© 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. 62199
    Prev
    Next
    INDEX
    Explanations

    sequences starting with here are or are meant

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

    positive descriptions or states

    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
    当时
    0.47
    или
    0.47
    ాత
    0.46
     ব্যক্তি
    0.46
    ヴィトン
    0.45
    არს
    0.44
    緒
    0.44
    ρι
    0.43
    শত
    0.43
    メニュー
    0.43
    POSITIVE LOGITS
    ed
    0.54
    édé
    0.47
    ena
    0.46
    ermat
    0.44
     and
    0.43
     நிறு
    0.43
     én
    0.43
    orithm
    0.42
     ने
    0.42
     கிற
    0.42
    Activations Density 0.000%

    No Known Activations