© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104676
    Prev
    Next
    INDEX
    Explanations

    specific file markers, question starts, or place names

    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
    薦
    -1.06
     venner
    -1.01
    紫色
    -1.00
    垢
    -0.98
     Juillet
    -0.96
    CHANNELS
    -0.96
     enigma
    -0.94
    FRAGMENT
    -0.93
    S
    -0.92
     discer
    -0.91
    POSITIVE LOGITS
    を探す
    1.17
     domande
    1.05
     réparer
    1.03
    Répondre
    1.03
    wej
    1.03
     мужская
    1.02
     empê
    1.02
    Ndr
    1.02
     combattre
    1.02
     particolarmente
    1.00
    Activations Density 0.001%

    No Known Activations