© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35326
    Prev
    Next
    INDEX
    Explanations

    References followed by list items

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

    The neuron fires on standalone numeric tokens—especially large numbers like the reference‐count figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     pinta
    -1.24
    haviours
    -1.22
     caricatura
    -1.16
    栞
    -1.16
    ṝ
    -1.14
    itiers
    -1.13
     inger
    -1.13
    iseerd
    -1.13
    桡
    -1.13
     biblia
    -1.12
    POSITIVE LOGITS
     and
    2.33
    4
    1.19
    0
    1.17
     überprüft
    1.16
    7
    1.16
    6
    1.15
    3
    1.14
     gelangt
    1.14
    1
    1.13
    5
    1.11
    Activations Density 0.010%

    No Known Activations