© 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. 591
    Prev
    Next
    INDEX
    Explanations

    variable names like s, k, u, i, h, p

    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
    thrower
    -0.88
    czywiście
    -0.80
     लगभग
    -0.79
    ítez
    -0.79
     singers
    -0.79
     hábiles
    -0.77
     нему
    -0.76
     reves
    -0.75
     seamlessly
    -0.74
    ַי
    -0.74
    POSITIVE LOGITS
    ießen
    0.86
    PLEMENT
    0.85
    ása
    0.84
    cterms
    0.84
    LOOKUP
    0.79
    ROGEN
    0.79
    enya
    0.79
     ovunque
    0.78
     errands
    0.76
     hulle
    0.76
    Activations Density 0.065%

    No Known Activations