© 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. 35144
    Prev
    Next
    INDEX
    Explanations

    value or values

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

    creation date

    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
     நாடுகளில்
    0.51
     angl
    0.50
     વિદ્ય
    0.48
     lacrosse
    0.46
     миллионов
    0.46
    ขับ
    0.46
    苅
    0.45
    نجليزية
    0.45
    REQUIRE
    0.45
     нож
    0.44
    POSITIVE LOGITS
    ，
    0.59
    brace
    0.50
    दि
    0.45
    value
    0.45
    ،
    0.44
    fda
    0.44
    valued
    0.43
     கத
    0.43
    ped
    0.43
    meth
    0.42
    Activations Density 0.000%

    No Known Activations