© 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. 57914
    Prev
    Next
    INDEX
    Explanations

    familiar sources said

    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
     a
    -1.24
    arza
    -0.88
     offensichtlich
    -0.87
     ständig
    -0.85
    许多
    -0.85
     ഒരു
    -0.84
     Gesetze
    -0.82
    Arri
    -0.82
    loč
    -0.81
     Umständen
    -0.81
    POSITIVE LOGITS
     close
    1.93
     who
    1.55
     involved
    1.46
     familiar
    1.38
     said
    1.34
    close
    1.21
     privy
    1.20
    Close
    1.16
     Close
    1.16
     acquainted
    1.07
    Activations Density 0.017%

    No Known Activations