© 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. 98848
    Prev
    Next
    INDEX
    Explanations

    many more, pressure washing

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

    descriptive observations and logical steps

    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
    rowse
    0.53
    ate
    0.48
     cultivar
    0.45
    awak
    0.45
    irling
    0.45
    ･
    0.44
    liet
    0.44
    que
    0.43
    in
    0.43
    Fly
    0.42
    POSITIVE LOGITS
    يف
    0.52
     ل
    0.49
    كر
    0.49
    的時候
    0.48
     chung
    0.48
     vez
    0.47
     infr
    0.47
    助力
    0.47
    ंद
    0.47
     gó
    0.46
    Activations Density 0.000%

    No Known Activations