© 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. 61412
    Prev
    Next
    INDEX
    Explanations

    first quarter

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

    precedes elaboration

    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
    𝑬
    0.48
     basins
    0.47
    Най
    0.47
     basalt
    0.45
    温泉
    0.44
     নায়
    0.44
    ИН
    0.44
    рг
    0.44
     crater
    0.44
    Cv
    0.44
    POSITIVE LOGITS
    toJSON
    0.48
    ought
    0.41
    いくつか
    0.41
     ২৬
    0.41
    撐
    0.40
    兩種
    0.39
    ২৪
    0.39
    AppConstant
    0.39
    ნიშვნ
    0.38
    buttonBar
    0.38
    Activations Density 0.000%

    No Known Activations