© 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. 144882
    Prev
    Next
    INDEX
    Explanations

    objects to move

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

    details, potential, tricky, extensions, detailed

    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
    氿
    0.47
    芑
    0.46
     ți
    0.44
    ហេ
    0.44
    铱
    0.44
     prób
    0.43
    㓞
    0.43
     práce
    0.43
    赟
    0.43
     corretamente
    0.42
    POSITIVE LOGITS
    ff
    0.50
     fonctionnal
    0.48
    म
    0.46
    han
    0.46
    0.46
     आंच
    0.45
     blockers
    0.45
    systems
    0.44
    frac
    0.44
    redirect
    0.44
    Activations Density 0.002%

    No Known Activations