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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54332
    Prev
    Next
    INDEX
    Explanations

    weather conditions and intensity

    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
    <bos>
    -1.29
     habilidad
    -1.25
     методы
    -1.11
     initComponents
    -1.08
    avedra
    -1.06
    ഢ
    -1.02
    authToken
    -0.99
     achievable
    -0.98
     individus
    -0.98
     correc
    -0.97
    POSITIVE LOGITS
     September
    1.42
     February
    1.36
     winter
    1.23
     autumn
    1.23
     July
    1.22
     Only
    1.21
     Both
    1.20
     November
    1.20
    Both
    1.19
     didn
    1.17
    Activations Density 0.071%

    No Known Activations