© 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. 53963
    Prev
    Next
    INDEX
    Explanations

    Transformer, Optional, date, Leo

    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
    变化的
    0.42
     Euros
    0.39
    事情
    0.39
    awati
    0.39
    GT
    0.38
    PRE
    0.38
    内容は
    0.37
    |,
    0.37
     Rajas
    0.37
    ürdig
    0.36
    POSITIVE LOGITS
     コーヒー
    0.44
    bbene
    0.42
     pneumatic
    0.42
     sipping
    0.41
     entspre
    0.41
     tubing
    0.41
     air
    0.40
     fibra
    0.40
     antibiot
    0.40
     ибо
    0.40
    Activations Density 0.016%

    No Known Activations