© 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. 138125
    Prev
    Next
    INDEX
    Explanations

    league average

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

    hardware, BIOS, renovate, cleanup

    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
    an
    0.52
    a
    0.51
    ak
    0.46
    ap
    0.46
    anonymous
    0.46
    aS
    0.44
    Anonymous
    0.44
    ert
    0.43
    esist
    0.43
    Tutorial
    0.42
    POSITIVE LOGITS
     これらの
    0.53
     waardoor
    0.53
    파일
    0.49
    ieważ
    0.48
    碖
    0.48
     fijn
    0.47
    攏
    0.46
     یہ
    0.46
     beschikbaar
    0.46
    效应
    0.46
    Activations Density 0.000%

    No Known Activations