© 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. 244201
    Prev
    Next
    INDEX
    Explanations

    box document directory precisely graft

    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
     Surprisingly
    0.50
    Remark
    0.48
     principales
    0.47
     Fortunately
    0.47
    n
    0.47
     compose
    0.45
     نصف
    0.45
    坵
    0.45
     النصوص
    0.45
     Remarkably
    0.44
    POSITIVE LOGITS
    athin
    0.46
    菇
    0.45
    ளர்
    0.44
    жити
    0.43
    你在
    0.42
    쩔
    0.42
    кау
    0.42
     frogs
    0.42
    كة
    0.41
    独
    0.41
    Activations Density 0.000%

    No Known Activations