© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180237
    Prev
    Next
    INDEX
    Explanations

    requirements and conditions

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

    limitless but not

    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
    Negative Logits
    tLogRow
    0.46
     μέσω
    0.43
    ਸ਼
    0.42
    榮
    0.42
     художник
    0.41
    𝑽
    0.41
    鈴木
    0.41
     Kaleidoscope
    0.40
    飼
    0.40
     kaleidoscope
    0.40
    POSITIVE LOGITS
     suspects
    0.49
    3
    0.47
     Requires
    0.44
     require
    0.44
     موارد
    0.43
     requires
    0.43
    require
    0.42
     cautions
    0.42
     candidates
    0.41
     certification
    0.41
    Activations Density 0.001%

    No Known Activations