© 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. 168880
    Prev
    Next
    INDEX
    Explanations

    shapeshifting

    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
     C
    0.52
    ing
    0.51
    five
    0.46
     assorted
    0.46
     rédu
    0.46
    las
    0.43
     Superf
    0.43
    is
    0.43
     disorders
    0.43
     including
    0.43
    POSITIVE LOGITS
    社會
    0.49
    Académie
    0.48
    หมือน
    0.46
    来看看
    0.45
    㓦
    0.45
     फार्म
    0.45
     ფედერ
    0.44
    䏍
    0.44
    烺
    0.44
     också
    0.44
    Activations Density 0.006%

    No Known Activations