© 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. 62418
    Prev
    Next
    INDEX
    Explanations

    year historic, goat hair, coloured marble

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

    impact, direction, global

    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
    व
    0.47
    рованные
    0.46
    య
    0.45
    랜드
    0.45
    ž
    0.44
    িনিয়ার
    0.44
    特集
    0.43
     žel
    0.43
    ৩
    0.43
    ਟ
    0.43
    POSITIVE LOGITS
     Пол
    0.49
     adjudged
    0.48
     மது
    0.47
    ẵn
    0.46
     orchestrated
    0.46
     recorded
    0.46
     illegitimate
    0.46
    nth
    0.45
     admitting
    0.45
    pia
    0.45
    Activations Density 0.000%

    No Known Activations