© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212220
    Prev
    Next
    INDEX
    Explanations

    details and lists

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьо
    0.47
     Sediment
    0.46
     Drought
    0.46
    HIGHLIGHT
    0.46
     Під
    0.42
     કોઈપણ
    0.41
    ت
    0.41
    Lock
    0.40
    بد
    0.40
    }]\
    0.40
    POSITIVE LOGITS
    श्रे
    0.52
     footnote
    0.52
     श्रेणियों
    0.51
    ᓲ
    0.51
     বৎসরের
    0.50
     Lillian
    0.50
    ynthia
    0.48
     yıll
    0.48
     redacted
    0.47
     conveys
    0.47
    Activations Density 0.000%

    No Known Activations