© 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. 245924
    Prev
    Next
    INDEX
    Explanations

    Church of Christ Care Center

    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
    ўцаў
    0.49
    쌔
    0.46
    delivered
    0.46
    قع
    0.46
    쌍
    0.46
    тоў
    0.45
    ويس
    0.45
    ว์
    0.45
    ўкі
    0.45
    벧
    0.44
    POSITIVE LOGITS
     ဗ
    0.55
     Crohn
    0.54
    esk
    0.52
    ao
    0.50
    AF
    0.49
     V
    0.49
     Valenc
    0.49
    om
    0.49
    ek
    0.48
     Pong
    0.48
    Activations Density 0.000%

    No Known Activations