© 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. 5744
    Prev
    Next
    INDEX
    Explanations

    periodicals and organizations

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

    language, license, keys

    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
     badass
    0.40
     Godzilla
    0.40
     DevOps
    0.40
    hhh
    0.39
     fucked
    0.38
    🔥
    0.36
    💪
    0.36
     và
    0.35
    hhhh
    0.35
     gestione
    0.35
    POSITIVE LOGITS
     periodicals
    0.34
    觀眾
    0.34
     memoranda
    0.33
     publicity
    0.33
     구분
    0.33
     الاطلاع
    0.32
     иных
    0.32
     외국
    0.31
    刊行
    0.31
     reprint
    0.31
    Activations Density 0.000%

    No Known Activations