© 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. 111626
    Prev
    Next
    INDEX
    Explanations

    asking about authors, bands, or clothes

    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
    <unused520>
    0.50
     ㄱ
    0.47
    shunt
    0.47
    corper
    0.46
    MktCap
    0.46
    olique
    0.46
     könne
    0.46
    🦟
    0.45
     nahil
    0.45
    出来ます
    0.45
    POSITIVE LOGITS
     e
    0.58
     la
    0.47
    獅
    0.47
     d
    0.45
     stressed
    0.45
     have
    0.44
     bad
    0.43
     use
    0.43
     expression
    0.43
     HAZ
    0.43
    Activations Density 0.001%

    No Known Activations