© 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. 224163
    Prev
    Next
    INDEX
    Explanations

    scientific journal articles and computations

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

    entity states processes

    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
     æ
    0.51
     WIT
    0.46
     የወ
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    కు
    0.43
     مد
    0.43
     কুমার
    0.43
     CHILD
    0.43
     ROSE
    0.43
     மற்றும்
    0.43
    POSITIVE LOGITS
    碛
    0.46
     whatnot
    0.43
     রেজিম
    0.43
    ormap
    0.41
    াইজ
    0.41
    件事
    0.40
    忱
    0.40
    喁
    0.39
    ajos
    0.39
    idiu
    0.39
    Activations Density 0.000%

    No Known Activations