© 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. 349
    Prev
    Next
    INDEX
    Explanations

    length, size, count of items

    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
     comprando
    -1.20
     ensimmä
    -1.06
     herunterladen
    -1.05
     vlieg
    -1.05
    firmasi
    -1.05
     immediatamente
    -0.98
     consape
    -0.98
     herbst
    -0.97
     precedenti
    -0.97
     elämä
    -0.97
    POSITIVE LOGITS
    もしか
    1.08
     but
    1.03
     G
    0.90
    H
    0.90
     createSprite
    0.90
    ながらも
    0.89
    Th
    0.88
    Get
    0.88
    ไลน์
    0.87
    There
    0.87
    Activations Density 0.007%

    No Known Activations