© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29133
    Prev
    Next
    INDEX
    Explanations

    TruthSeeker usernames

    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
     Stewardship
    0.33
    糁
    0.33
     Statistical
    0.31
     supplementing
    0.30
     Strengthening
    0.30
     Newsletter
    0.30
    <b>
    0.30
    newblock
    0.29
     Homepage
    0.29
     reconsideration
    0.29
    POSITIVE LOGITS
    ut
    0.36
    itty
    0.33
    z
    0.32
    ্যান
    0.31
    ập
    0.31
     thugs
    0.31
    arni
    0.31
     fanatics
    0.31
     maniak
    0.30
     všech
    0.30
    Activations Density 0.013%

    No Known Activations