© 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. 231921
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     passato
    0.45
    車
    0.43
    Ř
    0.42
    लो
    0.41
    Ż
    0.41
    ಾಯ
    0.40
     dürfen
    0.40
    時間が
    0.40
     suspensión
    0.39
    </sup>
    0.38
    POSITIVE LOGITS
     秒
    0.48
     کرنے
    0.43
    стве
    0.42
    虽然
    0.42
    ：（
    0.42
     biodiversity
    0.40
     \,\
    0.40
     עם
    0.40
    ታዊ
    0.40
     με
    0.39
    Activations Density 0.003%

    No Known Activations