© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128754
    Prev
    Next
    INDEX
    Explanations

    also

    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
     should
    -1.22
     trying
    -1.12
     people
    -1.09
     if
    -1.09
     just
    -1.08
     võib
    -1.02
     might
    -0.99
    取って
    -0.96
    j
    -0.96
     perhaps
    -0.95
    POSITIVE LOGITS
     also
    1.95
     также
    1.86
     également
    1.66
     також
    1.58
     también
    1.42
     También
    1.41
     cũng
    1.41
     também
    1.40
     and
    1.38
     také
    1.35
    Activations Density 0.046%

    No Known Activations