© 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. 43445
    Prev
    Next
    INDEX
    Explanations

    dumpster rental and waste disposal

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

    building, impacts, Tacitus, Scaliger, used

    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
    ﹊
    0.46
    دا
    0.43
    訪問
    0.43
    支部
    0.39
     iniciado
    0.39
    ブログ
    0.38
    ️
    0.38
    🎄
    0.38
    ਫ਼
    0.38
    宴
    0.38
    POSITIVE LOGITS
     मानक
    0.47
     சரியான
    0.46
     \$
    0.46
     muszą
    0.45
     உலகின்
    0.45
    leveland
    0.45
     dreaded
    0.45
     மாசு
    0.44
     기타
    0.43
     feared
    0.43
    Activations Density 0.000%

    No Known Activations