© 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. 102837
    Prev
    Next
    INDEX
    Explanations

    structs and sensitive materials

    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
    fiche
    -1.02
     nomor
    -0.81
    🚓
    -0.79
     Kann
    -0.77
     проблеми
    -0.72
    ξη
    -0.70
     nast
    -0.69
    bande
    -0.69
     Nase
    -0.69
     NEED
    -0.68
    POSITIVE LOGITS
     []:
    0.90
    TRAILING
    0.85
    tium
    0.85
    utiva
    0.84
     scel
    0.83
    ══
    0.82
    ショ
    0.80
     μεγ
    0.79
    *********/
    0.77
     "..\..\..\
    0.77
    Activations Density 0.008%

    No Known Activations