© 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. 8060
    Prev
    Next
    INDEX
    Explanations

    quantities and units

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

    quantities or units of measure

    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
    زاء
    0.39
     करोड़ों
    0.37
    喩
    0.35
     quelqu
    0.34
    fos
    0.34
     जिज्ञासा
    0.34
    耆
    0.34
     billions
    0.34
    友人
    0.33
    妖
    0.33
    POSITIVE LOGITS
    씩
    0.53
     including
    0.51
    ずつ
    0.48
     incluindo
    0.47
    nyi
    0.43
     அளவில்
    0.41
    ų
    0.40
     divided
    0.40
     včetně
    0.39
     கொண்ட
    0.39
    Activations Density 0.084%

    No Known Activations