© 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. 77370
    Prev
    Next
    INDEX
    Explanations

    multi-language text

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

    Italian invasion

    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
     slaughter
    0.46
     crouching
    0.46
    ]}{
    0.43
    രംഭ
    0.42
     ಪೊ
    0.41
    ]$.
    0.41
     curtains
    0.41
     నుండి
    0.40
    _{-}$
    0.40
     abundances
    0.40
    POSITIVE LOGITS
    гідно
    0.52
    ими
    0.46
     согласно
    0.46
    代表人
    0.45
     อาท
    0.45
    :
    0.43
    欬
    0.43
    eseen
    0.42
    ético
    0.42
     осо
    0.42
    Activations Density 0.003%

    No Known Activations