© 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. 62544
    Prev
    Next
    INDEX
    Explanations

    title followed by names

    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
    Negative Logits
     enrolment
    -0.73
     dolayı
    -0.71
    utilisateur
    -0.70
     Leeuwen
    -0.69
    iedades
    -0.69
    ReadInt
    -0.68
    TAKE
    -0.67
    LEVEL
    -0.67
    便秘
    -0.67
    Ekster
    -0.67
    POSITIVE LOGITS
    search
    0.88
     search
    0.70
    Center
    0.69
     Ay
    0.69
    refresh
    0.69
    kin
    0.68
    cle
    0.67
     большо
    0.67
    my
    0.66
    paste
    0.66
    Activations Density 0.072%

    No Known Activations