© 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. 53228
    Prev
    Next
    INDEX
    Explanations

    purchase/acquisition likelihood

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

    accurate coding

    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
    üks
    0.46
    実際
    0.44
    industrial
    0.43
    бет
    0.43
    気の
    0.43
    केट
    0.41
    ก่อ
    0.41
    ⴳ
    0.41
     නිෂ්පා
    0.41
    シューズ
    0.40
    POSITIVE LOGITS
     qubit
    0.45
     mohou
    0.44
     ensimmä
    0.44
     ketemu
    0.43
     Copy
    0.43
     Swim
    0.43
     Direction
    0.42
    ్య
    0.41
     Wich
    0.40
     swim
    0.40
    Activations Density 0.000%

    No Known Activations