© 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. 204413
    Prev
    Next
    INDEX
    Explanations

    sculpting, you, about, deal, regular, app, jaw

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

    project, toml, right

    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
     употреб
    0.44
    행
    0.43
    ЕС
    0.42
    ковского
    0.42
    τής
    0.42
    사진
    0.42
     intending
    0.40
    점이
    0.40
     الدهون
    0.40
    非
    0.40
    POSITIVE LOGITS
     ブランド
    0.46
     সরিয়ে
    0.46
     aconteceu
    0.43
    เรื่อง
    0.43
    াদেশ
    0.43
     設定
    0.43
    隔離
    0.43
     afterlife
    0.42
    镰
    0.42
     escenario
    0.42
    Activations Density 0.000%

    No Known Activations