© 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. 8511
    Prev
    Next
    INDEX
    Explanations

    icmp and .minecraft

    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
    RIDES
    0.33
    觞
    0.33
     isEqualToString
    0.31
    .)..
    0.31
    歟
    0.30
    Reilly
    0.29
    Grady
    0.29
    昻
    0.29
    鲑
    0.29
    toBottomOf
    0.29
    POSITIVE LOGITS
     This
    0.53
     Example
    0.51
    This
    0.49
     Using
    0.46
     this
    0.45
     using
    0.45
     simple
    0.45
    this
    0.44
     basic
    0.44
     acest
    0.44
    Activations Density 0.445%

    No Known Activations