© 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-262K
    7. 9853
    Prev
    Next
    INDEX
    Explanations

    Kohati Chappal

    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
     बातम्या
    0.48
    ਜ
    0.47
    ໝ
    0.47
    ส
    0.45
    యోజ
    0.44
    Voting
    0.44
    ρα
    0.44
     방송
    0.44
    ሳ
    0.44
    ს
    0.43
    POSITIVE LOGITS
    yel
    0.47
     aggressive
    0.43
     nutr
    0.43
     petri
    0.43
     cris
    0.42
    OGR
    0.42
     reiterate
    0.42
     res
    0.42
     laborers
    0.42
     creat
    0.41
    Activations Density 0.002%

    No Known Activations