© 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. 61761
    Prev
    Next
    INDEX
    Explanations

    possessive 'our' or 'by'

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

    block development, logging, code, rulers

    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
    achadh
    0.53
    ylabel
    0.52
    الية
    0.51
    ases
    0.50
    ө
    0.49
    ação
    0.48
    ermont
    0.47
    isão
    0.46
    aidh
    0.46
     وبه
    0.46
    POSITIVE LOGITS
    𝗟
    0.48
    ⁴
    0.45
     phúc
    0.44
    Honestly
    0.43
     налич
    0.43
    ❰
    0.43
    ろしく
    0.43
    私が
    0.42
    ⚌
    0.42
     filosof
    0.42
    Activations Density 0.000%

    No Known Activations