© 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. 212751
    Prev
    Next
    INDEX
    Explanations

    short dossier, interested in, video mash, years, card consolidation

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

    mapping or noise

    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
    መል
    0.54
    वि
    0.52
    В
    0.52
    基督
    0.51
    कृपया
    0.49
    А
    0.48
    वी
    0.48
    एक
    0.47
    𝄞
    0.47
    暾
    0.47
    POSITIVE LOGITS
    ir
    0.54
    rió
    0.52
    intensity
    0.51
    remo
    0.49
    classified
    0.49
    entos
    0.49
    cm
    0.48
    classify
    0.48
    chn
    0.46
    focused
    0.46
    Activations Density 0.000%

    No Known Activations