© 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. 28123
    Prev
    Next
    INDEX
    Explanations

    internal purposesbeautiful newhere certainlyon Chilika lake

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

    different types

    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
    फिल्म
    0.55
    й
    0.49
     স্বীকৃতির
    0.47
     Silicone
    0.45
     тех
    0.45
    ంబేద్కర్
    0.45
     `=`
    0.44
     Gọi
    0.44
    रेडी
    0.44
    কিন
    0.43
    POSITIVE LOGITS
    istem
    0.49
    łos
    0.47
    s
    0.47
    aschen
    0.47
    amar
    0.46
    proken
    0.46
    ross
    0.45
    segn
    0.45
    ssen
    0.44
    ebi
    0.44
    Activations Density 0.000%

    No Known Activations