© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110826
    Prev
    Next
    INDEX
    Explanations

    punishment 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
    permit
    -0.88
    湯
    -0.85
    conio
    -0.82
     scrittore
    -0.82
     armis
    -0.82
     Permit
    -0.81
     Angebote
    -0.81
    claimers
    -0.80
    าศ
    -0.79
     decrypt
    -0.78
    POSITIVE LOGITS
     imposed
    2.02
     inflicted
    1.61
     levied
    1.38
    imposed
    1.35
     impose
    1.30
     severity
    1.27
     administered
    1.16
    impose
    1.13
     imposition
    1.13
     prescribed
    1.10
    Activations Density 0.026%

    No Known Activations