© 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. 51226
    Prev
    Next
    INDEX
    Explanations

    full refund

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

    making or preparing text

    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
     бу
    0.46
    ウェア
    0.45
    स्टन
    0.45
    ्यूम
    0.44
    鋈
    0.44
    芴
    0.44
    రగ
    0.44
     крем
    0.43
     cultivating
    0.42
     articulating
    0.42
    POSITIVE LOGITS
    ss
    0.53
     poisoned
    0.49
    al
    0.49
    delt
    0.48
    spor
    0.47
    p
    0.46
    dns
    0.46
    getchar
    0.46
    vand
    0.46
    "
    0.45
    Activations Density 0.000%

    No Known Activations