© 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. 60437
    Prev
    Next
    INDEX
    Explanations

    John Chapman, coverage for

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

    gaming, states, cooking, devices, Undertale

    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
    yong
    0.49
    nes
    0.46
    le
    0.44
    are
    0.44
    上で
    0.44
    y
    0.43
    ☞
    0.43
    ame
    0.42
    ny
    0.42
    zon
    0.42
    POSITIVE LOGITS
     dizajn
    0.55
     clínicas
    0.47
    計
    0.47
     جشنواره
    0.47
     participar
    0.46
    审美
    0.46
    𒇽
    0.46
     metabolismo
    0.45
     especializados
    0.45
     hechas
    0.45
    Activations Density 0.000%

    No Known Activations