© 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. 156466
    Prev
    Next
    INDEX
    Explanations

    inherent properties

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

    banknotes, destructive, archival, artworks, banking

    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
    до
    0.46
    𝐥
    0.46
    𝓪
    0.44
    लीवुड
    0.43
    доро
    0.43
    ادي
    0.42
    𝐚
    0.42
    子上
    0.42
    过
    0.42
    挣
    0.42
    POSITIVE LOGITS
     skeletons
    0.48
     aram
    0.46
     analyt
    0.46
    toare
    0.46
     banknotes
    0.45
     artefacts
    0.44
     kaleidos
    0.43
     Banque
    0.43
     artworks
    0.43
     intermediaries
    0.43
    Activations Density 0.003%

    No Known Activations