© 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. 127626
    Prev
    Next
    INDEX
    Explanations

    specific word followed by specific punctuation or word

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

    stage of transformation

    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
    okra
    0.50
    phosph
    0.45
    țile
    0.44
    ogun
    0.43
    lardı
    0.43
    тету
    0.43
    㣙
    0.43
     套
    0.42
    ziak
    0.42
    🫧
    0.42
    POSITIVE LOGITS
     undergoes
    0.49
    သ
    0.48
     currentPlayer
    0.46
     cons
    0.46
    ﺍ
    0.46
    ICP
    0.45
    Stage
    0.45
     Schen
    0.44
     consac
    0.44
     stage
    0.44
    Activations Density 0.001%

    No Known Activations