© 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. 247931
    Prev
    Next
    INDEX
    Explanations

    activity, season, stories, market, streak

    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
     ಅ
    0.54
     開始
    0.54
     విడు
    0.51
    <unused604>
    0.51
    𒄷
    0.50
     والك
    0.50
    <unused533>
    0.49
     थी
    0.49
     toDo
    0.49
    AAF
    0.49
    POSITIVE LOGITS
    0.59
    สาว
    0.44
     Sains
    0.44
    <0x92>
    0.43
    Transportation
    0.43
    Merhaba
    0.42
     run
    0.42
     içerisinde
    0.41
    ทั่วไป
    0.41
    Kako
    0.40
    Activations Density 0.000%

    No Known Activations