© 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. 135014
    Prev
    Next
    INDEX
    Explanations

    income tax value

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

    not for

    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
     và
    0.44
    émique
    0.42
    _
    0.42
     người
    0.42
     Stok
    0.41
     thúc
    0.40
    强势
    0.40
    ন্তর
    0.40
    và
    0.40
    iende
    0.39
    POSITIVE LOGITS
     автомобиля
    0.53
     ALSO
    0.52
     차량
    0.52
    ཋ
    0.50
     автомобиль
    0.50
     ஏனெ
    0.49
     आल्सो
    0.49
    upra
    0.49
     GSi
    0.47
    驍
    0.47
    Activations Density 0.000%

    No Known Activations