© 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. 125999
    Prev
    Next
    INDEX
    Explanations

    David Livingstone’s

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

    regional variations

    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
    abá
    0.54
    s
    0.54
    甲
    0.49
    窗
    0.47
    sche
    0.47
    集
    0.47
    积极
    0.47
    忆
    0.47
     العربية
    0.46
    家长
    0.45
    POSITIVE LOGITS
     caster
    0.51
     promotion
    0.47
     enjo
    0.46
     galaxy
    0.46
    сиона
    0.46
     universe
    0.45
     recommand
    0.45
     assassination
    0.44
     लाख
    0.43
     explic
    0.43
    Activations Density 0.000%

    No Known Activations