© 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. 57031
    Prev
    Next
    INDEX
    Explanations

    apache license url

    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
     FRANCISCO
    -0.77
     Litu
    -0.77
     tull
    -0.73
    zné
    -0.73
    ISHOP
    -0.73
    tituts
    -0.73
     protagon
    -0.73
    尿
    -0.71
    RIC
    -0.70
     DHL
    -0.70
    POSITIVE LOGITS
     Apache
    1.43
     ASF
    1.31
    ASF
    1.20
    Apache
    1.09
     incubator
    0.99
    apache
    0.89
    pmc
    0.86
     PMC
    0.84
    incub
    0.84
    ยาว
    0.83
    Activations Density 0.529%

    No Known Activations