© 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. 63400
    Prev
    Next
    INDEX
    Explanations

    synchronized across

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

    compiling a list

    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
     foolish
    0.47
    grateful
    0.46
     cuja
    0.43
    Chief
    0.42
     खासतौर
    0.42
     Paula
    0.42
     Furn
    0.41
     votre
    0.41
    ❛
    0.40
    furn
    0.40
    POSITIVE LOGITS
     أيضًا
    0.52
     alleles
    0.47
     أيضا
    0.47
     కూడా
    0.46
     milliliters
    0.45
    也被
    0.44
    obacteria
    0.44
    但也
    0.43
    也
    0.43
     exhausted
    0.42
    Activations Density 0.000%

    No Known Activations