© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 4758
    Prev
    Next
    INDEX
    Explanations

    dramatically clutching

    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
    anio
    0.50
    reys
    0.47
    th
    0.47
    ro
    0.45
    २०
    0.45
    b
    0.44
    to
    0.44
    og
    0.43
    lla
    0.42
    टील
    0.42
    POSITIVE LOGITS
     aromas
    0.57
     elbows
    0.49
     sexy
    0.47
    ყოფ
    0.47
     shenanigans
    0.46
     amm
    0.45
     eins
    0.45
     তাই
    0.45
     hoş
    0.44
     Sly
    0.44
    Activations Density 0.000%

    No Known Activations