© 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. 4241
    Prev
    Next
    INDEX
    Explanations

    spring lineup

    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
    ла
    0.57
     आप
    0.57
    i
    0.57
     один
    0.53
     широкий
    0.53
     for
    0.52
     operador
    0.51
     ваш
    0.51
    o
    0.50
     আপনি
    0.50
    POSITIVE LOGITS
    CrL
    0.48
    Wür
    0.48
    fre
    0.47
    spe
    0.46
     rolle
    0.46
    Fre
    0.45
    Ga
    0.45
    Defense
    0.45
     عش
    0.43
    Zn
    0.42
    Activations Density 0.001%

    No Known Activations