© 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. 121333
    Prev
    Next
    INDEX
    Explanations

    bonus offers

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

    atomicity: one idea

    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
    у
    0.52
    q
    0.48
     Lovely
    0.48
    is
    0.47
     unsuccessful
    0.46
    hent
    0.44
    eas
    0.44
     Vj
    0.44
    ph
    0.43
    ш
    0.43
    POSITIVE LOGITS
    体
    0.48
     체
    0.47
     розви
    0.47
     توسعه
    0.45
     تضم
    0.45
     έργ
    0.45
     발전
    0.44
     входят
    0.44
    分别
    0.43
    账户
    0.43
    Activations Density 0.003%

    No Known Activations