© 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. 109507
    Prev
    Next
    INDEX
    Explanations

    Reagan, services, Resurrection

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

    postoperative changes, full cup, cosine, river

    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
     اولین
    0.46
     برضو
    0.43
     গাছের
    0.42
     cứng
    0.41
     Bxb
    0.41
     armor
    0.40
    唃
    0.40
     phục
    0.39
     Cũng
    0.39
     גם
    0.39
    POSITIVE LOGITS
    異常
    0.48
    uine
    0.47
    ELE
    0.47
    исто
    0.45
     moan
    0.45
    즈
    0.45
    ியோ
    0.45
    글
    0.45
    ELECT
    0.44
     disastrous
    0.44
    Activations Density 0.001%

    No Known Activations