© 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. 74406
    Prev
    Next
    INDEX
    Explanations

    found after certain things

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

    structured descriptions with colons

    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
    鹫
    0.54
    Oui
    0.50
    لاك
    0.50
    ോട്ട്
    0.49
    ტურ
    0.48
    ווי
    0.46
     കർ
    0.45
    ວິ
    0.45
     desktops
    0.45
     лінії
    0.45
    POSITIVE LOGITS
    ii
    0.51
     bagi
    0.49
     हवा
    0.46
    ih
    0.45
    ى
    0.44
    ţ
    0.44
    adeva
    0.43
     marks
    0.43
     সাম
    0.42
    ghijkl
    0.42
    Activations Density 0.000%

    No Known Activations