© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 175465
    Prev
    Next
    INDEX
    Explanations

    item descriptions following brand names

    np_acts-logits-general · gemini-2.5-flash-lite

    trench jacket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     importante
    0.52
     creciente
    0.51
    วันที่
    0.48
     d
    0.46
     muertos
    0.45
    [![
    0.45
     muerto
    0.44
    0.44
     como
    0.43
     animados
    0.42
    POSITIVE LOGITS
    bari
    0.50
    fler
    0.45
    änä
    0.45
    喹
    0.44
    ayla
    0.44
    Leod
    0.43
    следования
    0.42
    bahan
    0.42
     స్థాయి
    0.41
    ilden
    0.41
    Activations Density 0.003%

    No Known Activations