© 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. 59516
    Prev
    Next
    INDEX
    Explanations

    survived against, original casting

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

    dialogue and stories

    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
    ostro
    0.49
    examtype
    0.48
     ছই
    0.48
    চন্দ্রের
    0.47
    螈
    0.46
     شرطونه
    0.46
     stopni
    0.46
     সত্যাগ্রহ
    0.45
    錤
    0.45
    órica
    0.45
    POSITIVE LOGITS
    W
    0.58
     vicious
    0.57
    0.52
     downright
    0.50
     traumas
    0.50
    D
    0.49
    &
    0.49
     unfor
    0.48
     callous
    0.48
    Map
    0.47
    Activations Density 0.000%

    No Known Activations