© 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. 65953
    Prev
    Next
    INDEX
    Explanations

    year, date, place

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

    interactive projection surface

    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
     giv
    0.48
     tabuleiro
    0.44
     (')
    0.44
     হারানোর
    0.42
     evidenced
    0.41
     '(
    0.41
     __________
    0.41
     पंचायतों
    0.40
     ষে
    0.40
     prur
    0.40
    POSITIVE LOGITS
    寄
    0.52
     Hua
    0.49
    આ
    0.49
    சி
    0.48
    ப
    0.47
    ർ
    0.47
    த்த
    0.45
    ペ
    0.45
    చ
    0.45
    सा
    0.44
    Activations Density 0.000%

    No Known Activations