© 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. 6621
    Prev
    Next
    INDEX
    Explanations

    can, could, would

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

    detailed plans and projects

    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
    ल्ल
    0.45
    лды
    0.45
    ermark
    0.45
     स्टार्टिंग
    0.44
     मेला
    0.44
     interferometer
    0.43
    ش
    0.42
    ك
    0.41
    केंसी
    0.41
    ဂျ
    0.41
    POSITIVE LOGITS
     gön
    0.52
    null
    0.48
    setUp
    0.46
     吸
    0.46
     Dritt
    0.46
    __,
    0.45
     Blut
    0.45
     inclu
    0.45
    +]
    0.45
     INCLUDE
    0.45
    Activations Density 0.000%

    No Known Activations