© 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. 4171
    Prev
    Next
    INDEX
    Explanations

    what makes something individual

    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
    <unused2016>
    0.57
    🚛
    0.55
     экстре
    0.53
    
    0.53
    通常の
    0.50
     долларов
    0.49
    䡏
    0.49
    <unused303>
    0.48
     airliner
    0.48
    ◅
    0.47
    POSITIVE LOGITS
     wiem
    0.48
     ein
    0.47
    ,
    0.47
     wiecz
    0.46
    RI
    0.45
    J
    0.45
     evening
    0.44
     eben
    0.44
     be
    0.44
     In
    0.44
    Activations Density 0.001%

    No Known Activations