© 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. 76735
    Prev
    Next
    INDEX
    Explanations

    will ... not

    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
    르는
    0.49
     Cobra
    0.49
    ע
    0.49
    ک
    0.48
     Photographs
    0.47
    न
    0.47
     Oval
    0.46
     Powell
    0.45
     extraño
    0.45
    이
    0.45
    POSITIVE LOGITS
    issense
    0.48
     जुड़ा
    0.43
     தூ
    0.42
     defaultstate
    0.41
    oon
    0.40
     வலை
    0.40
    tront
    0.40
    ০০
    0.39
    ńskiego
    0.39
    |,
    0.38
    Activations Density 0.001%

    No Known Activations