© 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. 22-GEMMASCOPE-RES-131K
    7. 64645
    Prev
    Next
    INDEX
    Explanations

    program structure setup

    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_22/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
    corrhi
    -1.16
     bordados
    -1.09
     feier
    -1.06
     whether
    -1.05
     lápis
    -1.02
     kabát
    -1.02
     visualización
    -1.02
     zobac
    -1.02
     our
    -1.01
    visions
    -1.01
    POSITIVE LOGITS
     xbox
    0.91
     В
    0.85
    ？？
    0.79
     diep
    0.78
    ары
    0.76
    ("$.
    0.75
     /(\
    0.75
    hoek
    0.75
    zten
    0.75
     afore
    0.75
    Activations Density 0.010%

    No Known Activations