© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15794
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters

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

    Church, Progress, marble, and code snippets

    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_16k_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
    ’
    0.23
     approximates
    0.22
     volatiles
    0.21
     chars
    0.21
     blobs
    0.21
     anses
    0.21
     caches
    0.21
     shards
    0.21
     isotherms
    0.20
     conformations
    0.20
    POSITIVE LOGITS
    Д
    0.24
    а
    0.22
    о
    0.22
    А
    0.20
    і
    0.20
    си
    0.20
    Ми
    0.20
    Пи
    0.19
    ј
    0.19
    Б
    0.19
    Activations Density 0.000%

    No Known Activations