© 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. 114843
    Prev
    Next
    INDEX
    Explanations

    clinging prime minimum

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

    competitive approaches, pixel grid, serial dilution

    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
     porém
    0.49
     غوره
    0.48
    ริม
    0.47
    犇
    0.46
    ير
    0.45
    عيد
    0.45
    ysse
    0.44
     حسين
    0.44
    луч
    0.43
     основным
    0.42
    POSITIVE LOGITS
     Liberal
    0.55
    d
    0.51
    ad
    0.50
     Home
    0.49
    MS
    0.49
     route
    0.47
    Liberal
    0.47
    un
    0.46
     '<
    0.46
     Derivatives
    0.46
    Activations Density 0.000%

    No Known Activations