© 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. 196273
    Prev
    Next
    INDEX
    Explanations

    investigating markets

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

    consequences and states

    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
     증가
    0.52
     inform
    0.49
     빅
    0.48
     انتظ
    0.46
     अंदाजा
    0.46
    imismo
    0.45
     alegría
    0.45
     조
    0.44
     relieves
    0.43
     unrelenting
    0.43
    POSITIVE LOGITS
    ━━
    0.52
    trump
    0.49
    -
    0.46
    bling
    0.46
    แข่ง
    0.45
    ธรรม
    0.45
    </td>
    0.44
    Cré
    0.44
     Constitutional
    0.43
    )<-
    0.43
    Activations Density 0.001%

    No Known Activations