© 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. 184528
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    directly or actively

    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
     बिज़
    0.43
    फेस
    0.42
    鄉
    0.42
     મહિલા
    0.41
     GPA
    0.40
     penghargaan
    0.40
     فاطمه
    0.39
    Kerry
    0.39
    颔
    0.39
     пье
    0.38
    POSITIVE LOGITS
    ten
    0.48
    muy
    0.47
    sequent
    0.46
    块
    0.45
    єднання
    0.45
    தமாக
    0.44
    ignée
    0.44
    hány
    0.44
    m
    0.44
    lső
    0.43
    Activations Density 0.002%

    No Known Activations