© 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. 155677
    Prev
    Next
    INDEX
    Explanations

    band of

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

    checking availability

    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
    讒
    0.58
    ሠራ
    0.55
    чёт
    0.48
    言い
    0.47
    シル
    0.47
    いつでも
    0.47
    全文
    0.46
    ワー
    0.46
    RAS
    0.46
    لا
    0.46
    POSITIVE LOGITS
     a
    0.55
    edad
    0.52
     boldly
    0.51
     premi
    0.47
     richly
    0.47
     relegation
    0.47
    ism
    0.46
     legato
    0.46
    éis
    0.46
    fully
    0.46
    Activations Density 0.000%

    No Known Activations