© 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. 7777
    Prev
    Next
    INDEX
    Explanations

    numbers and prepositions

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

    lists with ratings and scores

    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
    と呼ばれる
    0.51
    霽
    0.50
     débit
    0.50
    明け
    0.49
    ľ
    0.49
    誤
    0.48
    лом
    0.47
    タイ
    0.47
     revêt
    0.47
     Baillargeon
    0.46
    POSITIVE LOGITS
    na
    0.59
    5
    0.57
    ni
    0.54
    6
    0.54
    7
    0.53
    Careers
    0.51
     yaş
    0.49
    soccer
    0.49
    ￠
    0.49
    lung
    0.48
    Activations Density 0.000%

    No Known Activations