© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 214527
    Prev
    Next
    INDEX
    Explanations

    credentials, license, workbook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mest
    0.39
     ď
    0.37
    🏇
    0.37
     Pal
    0.37
    क्षिक
    0.36
     >
    0.36
     garbage
    0.36
     >>>
    0.36
     Dominica
    0.36
     🥰
    0.36
    POSITIVE LOGITS
    สัมพันธ์
    0.42
     officer
    0.41
    撳
    0.40
    स्ताव
    0.39
     수정
    0.39
    cula
    0.38
    ajari
    0.38
    predictor
    0.37
     Officer
    0.36
    記者
    0.36
    Activations Density 0.000%

    No Known Activations