© 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. 155576
    Prev
    Next
    INDEX
    Explanations

    written on

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

    patterns in lists

    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
    ၇
    0.60
    შ
    0.49
     viciss
    0.47
    zwe
    0.47
    𝚣
    0.46
    वर्ष
    0.46
    整合
    0.45
     экономических
    0.45
     Хоккей
    0.44
    áin
    0.44
    POSITIVE LOGITS
     POR
    0.40
    คับ
    0.39
    %>
    0.39
     AUTO
    0.38
     Imperial
    0.37
    不做
    0.37
     tracers
    0.37
     Calculations
    0.36
    =""><
    0.36
    Locked
    0.36
    Activations Density 0.001%

    No Known Activations