© 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. 67880
    Prev
    Next
    INDEX
    Explanations

    STEP SIDE Gain Ask

    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
    now
    -0.98
     raisons
    -0.93
     ORGANIZATION
    -0.86
    говой
    -0.85
     voisins
    -0.85
    pení
    -0.83
    ecap
    -0.82
    
    -0.82
    いか
    -0.82
     giu
    -0.81
    POSITIVE LOGITS
     burgeoning
    0.82
    frutar
    0.79
     through
    0.73
     newOwner
    0.72
     camaraderie
    0.72
    ̓
    0.71
     ulong
    0.71
    𝙫
    0.70
    ActionPerformed
    0.70
    屠
    0.69
    Activations Density 0.003%

    No Known Activations