© 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. 66194
    Prev
    Next
    INDEX
    Explanations

    product alternatives or options

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

    sensory, risks, or system limits

    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
    }={\
    0.45
     accidental
    0.44
     شاه
    0.44
     scripted
    0.44
    شاه
    0.43
    ={[
    0.43
    পতি
    0.42
     explos
    0.42
     seaw
    0.42
    度
    0.42
    POSITIVE LOGITS
    mıştı
    0.53
     ಒಂದು
    0.50
     건설
    0.48
     முன்னர்
    0.48
     ગ્ર
    0.46
     커
    0.46
    尔
    0.46
     Están
    0.45
    커
    0.45
    aggreg
    0.45
    Activations Density 0.001%

    No Known Activations