© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73563
    Prev
    Next
    INDEX
    Explanations

    hybridization

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects the term "hybridization" in scientific contexts, particularly in genetic and molecular biology research.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of “hybrid” (especially in “hybridization,” “in situ hybridization,” etc.) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⎘
    -2.44
    !!”
    -2.42
    豋
    -2.25
    ”、“
    -2.20
    )";
    
    -2.16
    蟶
    -2.14
    埽
    -2.14
    镦
    -2.08
    ächst
    -2.03
    ⎚
    -2.03
    POSITIVE LOGITS
    2
    2.44
    3
    2.30
     the
    2.16
    1
    2.09
    s
    2.02
    )
    2.00
    <
    2.00
    9
    1.95
     inventive
    1.86
    [
    1.86
    Activations Density 0.014%

    No Known Activations