© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38443
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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
     oreilles
    -1.16
     doigts
    -1.14
    isst
    -0.97
     jambes
    -0.93
     presión
    -0.93
     disques
    -0.93
     acessórios
    -0.93
     bouteilles
    -0.92
     bēr
    -0.92
     tân
    -0.91
    POSITIVE LOGITS
    These
    0.94
    What
    0.85
     However
    0.85
    anças
    0.82
     very
    0.82
    Эти
    0.81
     With
    0.81
     quick
    0.80
     Bö
    0.80
     注意
    0.79
    Activations Density 0.004%

    No Known Activations