© 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. 107232
    Prev
    Next
    INDEX
    Explanations

    passed stringent

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

    tokens are pieces of words

    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
     تنها
    0.50
    ^{*}(\
    0.50
     biết
    0.47
    قتي
    0.47
     দিতে
    0.46
    的时间
    0.46
     conv
    0.44
    πει
    0.44
    rió
    0.44
    听到
    0.44
    POSITIVE LOGITS
    dus
    0.54
    anth
    0.53
    t
    0.49
    endid
    0.49
    sh
    0.49
    េទ
    0.48
    ensing
    0.47
    sight
    0.46
    station
    0.45
    town
    0.44
    Activations Density 0.001%

    No Known Activations