© 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. 178266
    Prev
    Next
    INDEX
    Explanations

    financial forecasts

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

    about what

    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
    진
    0.51
     frontera
    0.49
    
    0.46
     antire
    0.45
     quaternion
    0.45
    ‚
    0.45
    İstanbul
    0.44
    ʼn
    0.43
     reto
    0.42
    لوم
    0.42
    POSITIVE LOGITS
     Lakh
    0.46
    $}
    0.45
    dataType
    0.45
     ธ
    0.44
    ujjati
    0.44
    dH
    0.44
     Два
    0.44
    deprecated
    0.43
    чү
    0.43
    acariy
    0.43
    Activations Density 0.000%

    No Known Activations