© 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-65K
    7. 55249
    Prev
    Next
    INDEX
    Explanations

    emphasis and lists

    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
     refuge
    0.44
     และ
    0.43
     I
    0.42
    ibi
    0.41
     Erwach
    0.40
     adult
    0.38
     महत्त्वा
    0.38
     El
    0.38
     ดังนั้น
    0.38
    unna
    0.37
    POSITIVE LOGITS
    Heritage
    0.46
    Type
    0.46
    三国
    0.43
     avaient
    0.43
    Crazy
    0.42
    тров
    0.42
    Warnings
    0.41
    睇
    0.41
    Findings
    0.41
    除了
    0.40
    Activations Density 0.025%

    No Known Activations