© 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-65K
    7. 55374
    Prev
    Next
    INDEX
    Explanations

    you provide

    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_65k_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
    வுக்கு
    0.45
    pozy
    0.44
    நல்ல
    0.43
    शर
    0.43
    σί
    0.43
    弃
    0.42
    ᙱ
    0.42
    谨慎
    0.41
    𝔻
    0.41
    签证
    0.41
    POSITIVE LOGITS
    <0xCB>
    0.47
     Lin
    0.40
     Institute
    0.40
     €.
    0.40
     Mirza
    0.40
     Top
    0.40
     onu
    0.39
     h
    0.39
    ходя
    0.39
     nc
    0.39
    Activations Density 0.003%

    No Known Activations