© 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. 123741
    Prev
    Next
    INDEX
    Explanations

    no-marking feet

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

    only practical under conditions

    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
     Database
    0.48
    ffin
    0.45
     D
    0.45
     database
    0.44
     theory
    0.43
    로는
    0.43
     bodies
    0.43
     보다
    0.43
     Computer
    0.42
     pairing
    0.42
    POSITIVE LOGITS
    🧇
    0.47
    [`
    0.46
    ksh
    0.46
    extension
    0.46
     якому
    0.46
    shallow
    0.46
    longitude
    0.45
     кли
    0.45
    濺
    0.45
    _{+}$
    0.44
    Activations Density 0.001%

    No Known Activations