© 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. 152233
    Prev
    Next
    INDEX
    Explanations

    available from

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

    considerations, important

    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
    uzione
    0.49
    に関する
    0.49
    ങ്ങളാണ്
    0.45
    ニューヨーク
    0.45
    Scalar
    0.44
    ق
    0.44
    ット
    0.44
    など
    0.43
    などの
    0.43
    ተት
    0.42
    POSITIVE LOGITS
     COc
    0.48
     curses
    0.46
    блиоте
    0.46
     nghỉ
    0.44
     뭐
    0.43
    athed
    0.43
     लौटे
    0.42
     TRAILS
    0.42
     vở
    0.42
    锯
    0.42
    Activations Density 0.001%

    No Known Activations