© 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. 220024
    Prev
    Next
    INDEX
    Explanations

    gadgets, mobiles, coasters

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

    connecting terms and context

    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
    のに
    0.52
    ])))
    0.49
    示した
    0.47
    に対し
    0.47
    %%%%%%%%%%%%%
    0.46
    ledes
    0.44
     शिका
    0.43
    についての
    0.43
    ően
    0.43
    有利
    0.43
    POSITIVE LOGITS
     mobiles
    0.47
     gadgets
    0.46
    담당
    0.45
    Μ
    0.44
     triggers
    0.43
    isArray
    0.43
     abbreviations
    0.43
     coasters
    0.43
    γι
    0.43
    খণ্ড
    0.42
    Activations Density 0.000%

    No Known Activations