© 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. 31745
    Prev
    Next
    INDEX
    Explanations

    who wouldn't

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     never
    -1.72
     هیچ
    -1.53
    never
    -1.48
     only
    -1.42
    Never
    -1.30
     pouze
    -1.30
     nikdy
    -1.29
     Never
    -1.24
     hardly
    -1.24
     лишь
    -1.23
    POSITIVE LOGITS
     didn
    2.64
     not
    2.56
     isn
    2.53
     wasn
    2.48
     aren
    2.41
     weren
    2.39
     wouldn
    2.30
     doesn
    2.25
    Didn
    2.03
    Wasn
    2.02
    Activations Density 0.043%

    No Known Activations