© 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. 190870
    Prev
    Next
    INDEX
    Explanations

    Financial statements and sales figures

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

    things that are

    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
    ні
    0.51
    рование
    0.47
    P
    0.46
     and
    0.46
    هم
    0.45
    并
    0.45
     oun
    0.43
    保持
    0.43
     IOP
    0.43
    hese
    0.43
    POSITIVE LOGITS
     ކ
    0.45
     ketones
    0.42
    THAN
    0.41
    ච්
    0.41
     suppressant
    0.41
     কী
    0.40
    སྐ
    0.40
     cultivars
    0.40
    yendo
    0.40
     diuretics
    0.40
    Activations Density 0.000%

    No Known Activations