© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13273
    Prev
    Next
    INDEX
    Explanations

    proprietary waterproof, unlike older, Linux, C

    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
     BECAUSE
    0.43
    ﺛ
    0.42
    ভৃতি
    0.42
     സംവിധ
    0.41
     ಮಾಡಿ
    0.39
    AND
    0.39
    ENDMENT
    0.39
     LIMITED
    0.38
     SECOND
    0.38
     ANALYSIS
    0.38
    POSITIVE LOGITS
     gyak
    0.42
     zuverläss
    0.40
     bzw
    0.38
     Percolation
    0.38
     ول
    0.37
     (~
    0.36
     Mon
    0.36
     useful
    0.36
     parfois
    0.36
    များ
    0.35
    Activations Density 0.052%

    No Known Activations