© 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. 170272
    Prev
    Next
    INDEX
    Explanations

    constructs academic writing

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

    cost us / someone you

    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
     şek
    0.55
    鹂
    0.54
    ⤠
    0.53
     ilişk
    0.51
     nedenle
    0.45
    learning
    0.45
    ','"
    0.44
    `,`
    0.44
    ˏ
    0.44
     cặp
    0.43
    POSITIVE LOGITS
    ark
    0.59
    H
    0.53
    etaan
    0.51
    وت
    0.51
    ARK
    0.48
    1
    0.46
     Pl
    0.46
     Kru
    0.45
     Ком
    0.45
     Pla
    0.45
    Activations Density 0.000%

    No Known Activations