© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3316
    Prev
    Next
    INDEX
    Explanations

    transfer IN requirements tree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Suisse
    -0.77
    Bottom
    -0.67
     LOD
    -0.65
    ||||
    -0.65
    Ἥ
    -0.64
    glm
    -0.64
     Peterson
    -0.64
     キ
    -0.63
     durante
    -0.63
    地球
    -0.63
    POSITIVE LOGITS
     ulasan
    0.77
    ⅛
    0.76
     Smaller
    0.73
    мал
    0.69
    smaller
    0.68
     voordat
    0.68
     nieces
    0.67
     zicht
    0.66
     király
    0.66
    Exemples
    0.66
    Activations Density 0.063%

    No Known Activations