© 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. 85889
    Prev
    Next
    INDEX
    Explanations

    DeWit

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

    other or another

    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
    Not in Any Lists

    No Comments

    Negative Logits
    اکر
    0.52
     afgelopen
    0.51
    戻
    0.47
    ಂಗ
    0.47
    بیر
    0.46
    take
    0.45
    тать
    0.45
    افر
    0.45
    旷
    0.45
    hotmail
    0.44
    POSITIVE LOGITS
     distinctive
    0.52
    ión
    0.46
     發
    0.45
     armature
    0.44
    ámara
    0.44
     rostrum
    0.43
     γίνεται
    0.43
    лъ
    0.43
    铣
    0.42
     genitalia
    0.42
    Activations Density 0.001%

    No Known Activations