© 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. 227687
    Prev
    Next
    INDEX
    Explanations

    return masters make world

    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
     daños
    0.52
     amarilla
    0.52
     herk
    0.50
     habitantes
    0.49
     оско
    0.49
     রেজিস্ট্র
    0.48
     abitanti
    0.48
     ଭ
    0.48
    NESOTA
    0.47
    REAT
    0.47
    POSITIVE LOGITS
     Anschließend
    0.46
    ས
    0.46
     نیم
    0.45
     Halb
    0.45
    typ
    0.44
    ცი
    0.44
    nocześnie
    0.44
    웍
    0.42
    ัก
    0.41
    urno
    0.41
    Activations Density 0.000%

    No Known Activations