© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 115790
    Prev
    Next
    INDEX
    Explanations

    about a / justice / mess

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

    code structure initialization

    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
    mu
    0.47
    AHN
    0.45
     сохранить
    0.45
     ROT
    0.45
     Z
    0.45
     швидко
    0.43
    BOR
    0.43
    ASHI
    0.42
    boh
    0.42
    0
    0.42
    POSITIVE LOGITS
    íme
    0.53
     Pública
    0.45
    ახებ
    0.43
    ╭
    0.41
    ვის
    0.41
    کز
    0.41
    Probability
    0.41
     važ
    0.41
    オブ
    0.41
    バラ
    0.40
    Activations Density 0.000%

    No Known Activations