© 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. 132738
    Prev
    Next
    INDEX
    Explanations

    ONE teach form

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

    leading zeroes in spreadsheets

    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
     one
    0.50
     unincorporated
    0.47
     banding
    0.46
    ود
    0.45
    slf
    0.44
     a
    0.44
     folklor
    0.43
     böl
    0.43
    ِ
    0.43
     per
    0.42
    POSITIVE LOGITS
    铖
    0.52
    小于
    0.51
     ovipares
    0.51
     cathodes
    0.48
    ্যন্তরীণ
    0.48
    Aprend
    0.47
    aprend
    0.47
    夸
    0.46
     apprendre
    0.46
    üğünüz
    0.45
    Activations Density 0.001%

    No Known Activations