© 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. 120658
    Prev
    Next
    INDEX
    Explanations

    gift card, chapter narrative, accept charge

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

    constantly evolving

    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
    Zach
    0.50
    Detroit
    0.49
    本書
    0.47
     مستقل
    0.47
    اي
    0.46
    ᑯ
    0.45
    商
    0.45
    DR
    0.44
    1
    0.44
    座標
    0.44
    POSITIVE LOGITS
     flores
    0.51
     frontline
    0.45
     кори
    0.44
     sabbam
    0.43
     güneş
    0.43
    ద్ధి
    0.43
     Kullan
    0.43
     praised
    0.42
    нена
    0.42
     nudge
    0.42
    Activations Density 0.001%

    No Known Activations