© 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. 104309
    Prev
    Next
    INDEX
    Explanations

    financial agreements

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

    options provided in versions

    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
     I
    0.55
    andolo
    0.46
    ۹
    0.46
     jumpers
    0.45
     Ato
    0.45
     БД
    0.45
    itre
    0.44
    cadia
    0.44
     Nj
    0.44
     успеха
    0.44
    POSITIVE LOGITS
     nuo
    0.47
     Grundstück
    0.47
    ურთიერთ
    0.47
    LAH
    0.46
    桕
    0.46
    नगर
    0.46
     OBJECTTYPE
    0.45
    TSC
    0.44
    裹
    0.44
    票房
    0.44
    Activations Density 0.000%

    No Known Activations