© 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. 211125
    Prev
    Next
    INDEX
    Explanations

    ice fishing

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

    assumes a standard array

    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
     Zustimmung
    0.49
     성능
    0.49
     Fron
    0.48
    𝚕
    0.48
     標準
    0.47
     Cate
    0.47
     جوہری
    0.47
    莘
    0.47
    illeurs
    0.47
    fromParams
    0.46
    POSITIVE LOGITS
     hath
    0.45
     translations
    0.44
    خ
    0.43
     ores
    0.43
     proposes
    0.43
     sums
    0.42
     folds
    0.41
     marki
    0.41
    об
    0.40
     neglects
    0.40
    Activations Density 0.001%

    No Known Activations