© 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. 189127
    Prev
    Next
    INDEX
    Explanations

    redistributed by, changed, photograph, one reason, aged animation, supported ones

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

    string literals like "hello world"

    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
     クリーム
    0.47
    ToArray
    0.44
    ージェ
    0.43
    নমেন্ট
    0.42
    ORF
    0.41
    㹮
    0.40
     Farah
    0.40
    寧
    0.40
    Styl
    0.40
    混乱
    0.40
    POSITIVE LOGITS
    बांग
    0.47
     capitalist
    0.45
    तब
    0.44
    ppled
    0.43
    ᴙ
    0.43
     naval
    0.43
    த்திக்க
    0.42
    র্ম
    0.42
     dimin
    0.42
     आठ
    0.41
    Activations Density 0.001%

    No Known Activations