© 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. 55451
    Prev
    Next
    INDEX
    Explanations

    account, from, largest

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

    contrasts and alternatives

    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
     벗
    0.51
     expecting
    0.50
     abogado
    0.50
     Organiz
    0.49
     entrada
    0.48
     organizes
    0.48
     llamadas
    0.46
     ayrıca
    0.46
     powin
    0.46
     organizaciones
    0.46
    POSITIVE LOGITS
     間
    0.50
    ίο
    0.46
    ChooseServer
    0.44
    eworthy
    0.44
    ﹙
    0.43
    óz
    0.43
    Mosaic
    0.43
    Knife
    0.43
    线程
    0.43
    间隔
    0.42
    Activations Density 0.000%

    No Known Activations