© 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. 22005
    Prev
    Next
    INDEX
    Explanations

    vulnerability versions

    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
    讠
    0.41
    黼
    0.41
    ッセージ
    0.41
    itabbam
    0.39
    ůj
    0.39
    juč
    0.38
     לפי
    0.38
    lägt
    0.38
    徝
    0.38
     例えば
    0.38
    POSITIVE LOGITS
     alken
    0.39
     ikke
    0.39
     hippocampal
    0.39
    different
    0.38
     greater
    0.38
     siblings
    0.38
     neither
    0.38
     versions
    0.37
     outdoor
    0.37
    their
    0.36
    Activations Density 0.011%

    No Known Activations