© 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. 94670
    Prev
    Next
    INDEX
    Explanations

    financial and technical contexts

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

    means "open weight"

    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
    Ash
    0.53
    =
    0.50
    。
    0.48
     Ash
    0.46
     λογ
    0.46
    ，
    0.46
     Кали
    0.45
    Lah
    0.45
    ،
    0.45
    Tester
    0.45
    POSITIVE LOGITS
     obsess
    0.48
     తాజాగా
    0.45
     प्रणाम
    0.44
    <unused7>
    0.44
     autorità
    0.43
    éta
    0.42
     फिल
    0.42
     elég
    0.42
     බල
    0.42
    ನಾಡ
    0.42
    Activations Density 0.000%

    No Known Activations