© 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. 11975
    Prev
    Next
    INDEX
    Explanations

    individual financial security

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

    outlines plans roadmaps guidelines

    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
     broadcaster
    0.48
     criticize
    0.41
    dum
    0.41
    报告
    0.40
     wondrous
    0.40
    砭
    0.40
     profound
    0.39
     جہ
    0.39
    الإنجليزية
    0.39
    ┝
    0.39
    POSITIVE LOGITS
     envio
    0.55
    FormData
    0.52
    ();
    0.49
     unprotected
    0.49
     tropas
    0.48
     ጥላ
    0.48
     usado
    0.48
     умолчанию
    0.47
     enviados
    0.46
     பாதுகா
    0.46
    Activations Density 0.000%

    No Known Activations