© 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. 22291
    Prev
    Next
    INDEX
    Explanations

    dates and months

    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
    ScriptBuf
    0.58
    琇
    0.56
    RawO
    0.53
    ITAR
    0.52
     ইমরান
    0.50
    msgSender
    0.49
     टिश्यू
    0.49
     vaisseau
    0.49
    钯
    0.49
    麸
    0.48
    POSITIVE LOGITS
     calendar
    1.52
     calendars
    1.41
     Calendar
    1.28
    Calendar
    1.19
    calendar
    1.16
     seasonal
    1.14
     Calend
    1.14
     календар
    1.10
     कैलेंडर
    1.09
     calendário
    1.05
    Activations Density 0.136%

    No Known Activations