© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58145
    Prev
    Next
    INDEX
    Explanations

    red, benefits, advantages

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

    The neuron activates on words and morphemes referring to benefits, advantages, or positive outcomes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    倶楽部
    -0.66
     femininos
    -0.66
     önem
    -0.65
    曦
    -0.64
    progressDialog
    -0.64
    ோ
    -0.63
    фі
    -0.63
     basadas
    -0.63
    cloudy
    -0.63
    xdc
    -0.62
    POSITIVE LOGITS
     accrue
    2.88
     accru
    2.41
     red
    2.34
     accruing
    2.06
     accrued
    2.05
    red
    1.74
    Red
    1.65
    红
    1.59
    ured
    1.58
     inher
    1.50
    Activations Density 0.058%

    No Known Activations