© 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. 65505
    Prev
    Next
    INDEX
    Explanations

    highest quality

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

    numbers and specific terms

    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
     조정
    0.52
    வுகளை
    0.48
    kách
    0.47
    㗽
    0.47
     자신의
    0.47
     봐야
    0.47
     固定
    0.47
     공간
    0.46
     기존
    0.46
     สามารถ
    0.45
    POSITIVE LOGITS
    <0xAC>
    0.44
    鸳
    0.44
    ois
    0.44
    铅
    0.43
     bulldozer
    0.42
    í
    0.42
    çin
    0.42
    芝
    0.42
     spoken
    0.41
    iferous
    0.41
    Activations Density 0.001%

    No Known Activations