© 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. 179974
    Prev
    Next
    INDEX
    Explanations

    GUEST

    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
     निचे
    0.59
     opposites
    0.57
     ያስፈል
    0.54
     necessità
    0.54
     stå
    0.54
     셀
    0.54
     потребу
    0.52
    xcuserdata
    0.52
     свадь
    0.52
    acji
    0.51
    POSITIVE LOGITS
    ↵↵
    0.52
    干
    0.49
    Angel
    0.45
     Tool
    0.45
     Subs
    0.44
    等
    0.44
    GR
    0.44
    丁
    0.44
    ，
    0.43
    VR
    0.43
    Activations Density 0.000%

    No Known Activations