© 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. 158592
    Prev
    Next
    INDEX
    Explanations

    Provider Members

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

    materiality, recurrences, SAM, Mix

    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
     टाइप्स
    0.46
     uds
    0.45
     روم
    0.44
    냥
    0.44
    aktan
    0.43
     склон
    0.43
    ędzynarod
    0.42
     유
    0.41
     jaka
    0.41
     sombra
    0.41
    POSITIVE LOGITS
    म्मू
    0.52
    積
    0.52
    HAN
    0.51
    ్యాచ్
    0.51
    ಿಯೂ
    0.49
    慮
    0.49
    CAL
    0.46
     MAS
    0.46
    াকৃতিক
    0.46
    بوت
    0.45
    Activations Density 0.001%

    No Known Activations