© 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. 31-GEMMASCOPE-2-RES-262K
    7. 82330
    Prev
    Next
    INDEX
    Explanations

    carries information, sending data

    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_31_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
    ה
    0.53
    et
    0.49
    ado
    0.48
    etu
    0.47
    ato
    0.46
     auditors
    0.46
     refusal
    0.46
     bouquets
    0.46
     donors
    0.45
     deities
    0.45
    POSITIVE LOGITS
    蓄
    0.50
    Clothes
    0.49
    Clock
    0.44
    UserName
    0.44
    tenberg
    0.41
    Brian
    0.41
    лада
    0.40
     inger
    0.40
    DesignTime
    0.40
    期
    0.40
    Activations Density 0.001%

    No Known Activations