© 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. 29016
    Prev
    Next
    INDEX
    Explanations

    talking about technology

    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
     ;-)
    0.46
     более
    0.43
     november
    0.42
     더
    0.42
    ริม
    0.41
    resTmp
    0.41
    特别
    0.41
     하지만
    0.40
     थोडे
    0.40
    鏉
    0.40
    POSITIVE LOGITS
    Readable
    0.44
     समुदाय
    0.42
     coval
    0.41
     उसको
    0.40
    "',
    0.39
     regener
    0.39
     moistened
    0.39
     sesi
    0.38
     pastes
    0.38
    ွှ
    0.38
    Activations Density 0.011%

    No Known Activations