© 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. 93289
    Prev
    Next
    INDEX
    Explanations

    I might

    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
     was
    -1.38
     are
    -1.29
     didn
    -1.27
     were
    -1.23
     need
    -1.12
     kellett
    -1.06
     haven
    -1.04
    なくなった
    -1.03
    已经
    -1.03
     rarely
    -1.02
    POSITIVE LOGITS
    🤞
    1.12
     and
    1.05
     kanske
    1.02
     beserta
    0.98
    Then
    0.97
    switchTo
    0.93
    Maybe
    0.91
    🎄
    0.91
     tillsammans
    0.91
    🥇
    0.91
    Activations Density 0.035%

    No Known Activations