© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205182
    Prev
    Next
    INDEX
    Explanations

    retailer store Spirit Ralph

    np_acts-logits-general · gemini-2.5-flash-lite

    options, numbers, lists, or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    capability
    0.52
    芘
    0.48
    ＜
    0.47
    変
    0.47
    羮
    0.47
    撓
    0.46
    磨
    0.46
    ransition
    0.45
    られる
    0.44
    ясплат
    0.44
    POSITIVE LOGITS
     enquanto
    0.53
     um
    0.49
     incred
    0.48
     ناس
    0.46
     insignia
    0.46
     அவருடைய
    0.46
     entrop
    0.46
     Ling
    0.46
     דר
    0.46
    欳
    0.46
    Activations Density 0.000%

    No Known Activations