© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91719
    Prev
    Next
    INDEX
    Explanations

    laws and penalties

    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
     robbed
    -0.93
    واره
    -0.93
    вяз
    -0.91
    conio
    -0.90
    lecte
    -0.89
    orited
    -0.86
    tiendo
    -0.82
     "','
    -0.82
     controversy
    -0.82
    ugos
    -0.81
    POSITIVE LOGITS
     penalties
    3.00
     penalty
    2.63
     Penalties
    2.36
     punishments
    2.19
     Penalty
    2.19
     punishment
    2.16
     punishable
    2.16
    Penalty
    2.11
    penalty
    2.09
     vio
    1.86
    Activations Density 0.042%

    No Known Activations