© 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. 192129
    Prev
    Next
    INDEX
    Explanations

    . Additional , Jean , gun , needed , you

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

    multilingual examples

    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
    通過
    0.48
    </i>
    0.47
    特
    0.45
    求
    0.45
    集
    0.44
    zA
    0.44
    被
    0.44
    IO
    0.43
    Class
    0.43
    Pr
    0.42
    POSITIVE LOGITS
     балко
    0.49
    َاب
    0.49
     педагоги
    0.49
     зуб
    0.47
    ậu
    0.46
     Ngọc
    0.46
     Chúa
    0.46
     affiliations
    0.46
     insanların
    0.46
     animasi
    0.45
    Activations Density 0.000%

    No Known Activations