© 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. 126894
    Prev
    Next
    INDEX
    Explanations

    Yasushi, Jesus, offensive, away

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

    Welcome and introductions

    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
    ចាប់
    0.54
     മാറ്റ
    0.48
    Ƙ
    0.42
     Knudsen
    0.41
     kayaking
    0.40
     অপরাধ
    0.40
     남자
    0.39
     ribosomes
    0.39
     baseApiPath
    0.39
     forgiveness
    0.39
    POSITIVE LOGITS
    عمال
    0.43
    シール
    0.41
     fetish
    0.41
    attiv
    0.41
    厂
    0.41
    阎
    0.41
    ждению
    0.41
    캘
    0.41
     etiqu
    0.40
    Fet
    0.39
    Activations Density 0.000%

    No Known Activations