© 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. 113474
    Prev
    Next
    INDEX
    Explanations

    average per match

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

    browser APIs

    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
    о
    0.59
    ина
    0.51
    а
    0.51
    е
    0.51
    у
    0.49
    百
    0.49
    օ
    0.47
    ociaż
    0.47
    ο
    0.47
    ține
    0.47
    POSITIVE LOGITS
     etik
    0.50
     Estatal
    0.49
     anormal
    0.46
     خراب
    0.46
     adhesions
    0.45
     unim
    0.45
     unsound
    0.45
     pavilions
    0.44
     Tiles
    0.43
     undesired
    0.43
    Activations Density 0.000%

    No Known Activations