© 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. 22-GEMMASCOPE-RES-131K
    7. 575
    Prev
    Next
    INDEX
    Explanations

    blocking or preventing actions

    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_22/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
    Lex
    -0.89
     ओवर
    -0.81
    ortes
    -0.79
    ウール
    -0.78
    Leftrightarrow
    -0.77
    HDR
    -0.77
    iania
    -0.77
     serisi
    -0.76
     affichés
    -0.76
     såsom
    -0.76
    POSITIVE LOGITS
     otherwise
    1.84
     other
    1.47
    otherwise
    1.38
    Otherwise
    1.37
     if
    1.36
     Otherwise
    1.30
     previous
    1.27
     sonst
    1.21
     иначе
    1.14
     earlier
    1.10
    Activations Density 0.075%

    No Known Activations