© 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. 101559
    Prev
    Next
    INDEX
    Explanations

    dumpster rubbish washing countries global

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

    game actions, conditions, or recordings

    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
    ただし
    0.52
     alp
    0.50
    sole
    0.47
     eficaz
    0.47
    력
    0.46
     indist
    0.45
     sump
    0.45
     recid
    0.45
     eva
    0.45
     típ
    0.44
    POSITIVE LOGITS
    供应商
    0.47
    iy
    0.46
    রায়
    0.44
    國家
    0.44
    鎸
    0.44
    शैली
    0.43
    Ν
    0.43
    «
    0.42
    ému
    0.42
     वकील
    0.42
    Activations Density 0.000%

    No Known Activations