© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    legal judgments and proceedings

    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
     \#
    -0.93
     \&
    -0.91
     www
    -0.90
     $=$
    -0.90
    —
    -0.88
     $-$
    -0.83
     $^{\
    -0.81
    –
    -0.75
    ho
    -0.75
    gure
    -0.73
    POSITIVE LOGITS
     thérape
    0.94
    getreten
    0.93
    mortem
    0.91
    geschenk
    0.88
     akku
    0.88
    يست
    0.87
    Usted
    0.86
    kelt
    0.84
    δώ
    0.84
    führ
    0.83
    Activations Density 0.149%

    No Known Activations