© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47852
    Prev
    Next
    INDEX
    Explanations

    commerce and questions

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

    market value and probability comparisons

    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
    frac
    0.48
    therefore
    0.47
    р
    0.46
    JK
    0.43
    paragraph
    0.43
    ollow
    0.42
    fraction
    0.42
    ir
    0.41
    abut
    0.41
    subsection
    0.41
    POSITIVE LOGITS
    ราคา
    0.47
     Beyoncé
    0.46
    潵
    0.44
    价格
    0.44
    市值
    0.44
     sărb
    0.44
     ภาพ
    0.44
    节日
    0.44
     SpaceX
    0.43
    覦
    0.43
    Activations Density 0.000%

    No Known Activations