© 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. 36963
    Prev
    Next
    INDEX
    Explanations

    light on

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

    corporate valuation

    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
    大全
    0.47
    ul
    0.46
    itud
    0.44
    ives
    0.43
    -
    0.42
    ival
    0.42
    视觉
    0.42
    𝘩
    0.41
     tactile
    0.41
     short
    0.41
    POSITIVE LOGITS
    ož
    0.48
    ঙালি
    0.48
     Амери
    0.48
     Америка
    0.48
    瓔
    0.47
    াইট
    0.47
    adım
    0.47
     Ears
    0.46
     девочки
    0.46
    ERRY
    0.46
    Activations Density 0.000%

    No Known Activations