© 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. 85414
    Prev
    Next
    INDEX
    Explanations

    such as

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

    cause damage or indicate

    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
    按照
    0.47
     versions
    0.43
     「
    0.43
    党委
    0.43
     اختيار
    0.42
     opinions
    0.42
     version
    0.42
    Sdk
    0.42
    มี
    0.41
     schemas
    0.41
    POSITIVE LOGITS
     விடும்
    0.46
    ទ្
    0.46
     bå
    0.45
     பகுதி
    0.44
     Portion
    0.44
    āb
    0.44
    𒌓
    0.43
     곡
    0.43
    ędzynarod
    0.43
    िल
    0.43
    Activations Density 0.001%

    No Known Activations