© 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. 117552
    Prev
    Next
    INDEX
    Explanations

    short identifiers completing phrases

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

    GPT

    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
    ک
    0.98
    ي
    0.93
    ت
    0.91
    هم
    0.74
    あらゆる
    0.74
    engkap
    0.73
    т
    0.71
    त
    0.71
    اب
    0.70
     ۸
    0.70
    POSITIVE LOGITS
    ’
    1.00
    }$\
    0.77
    ד
    0.74
    ’”
    0.72
    -
    0.72
    Repost
    0.65
    ,
    0.65
    大
    0.64
    ^{*}$
    0.62
     produkt
    0.62
    Activations Density 1.865%

    No Known Activations