© 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. 26522
    Prev
    Next
    INDEX
    Explanations

    printable picturesproduct datamonthly levelsentertain guestssince childhood

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

    credentialing and resources

    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
     Кли
    0.50
    bank
    0.47
     CONNE
    0.47
     verme
    0.44
     Михаил
    0.44
    geti
    0.44
    ↵
    0.43
    uent
    0.43
    leti
    0.43
    unit
    0.42
    POSITIVE LOGITS
    痂
    0.50
    ㅇ
    0.49
    انہوں
    0.48
     nube
    0.47
    भाष
    0.46
    ك
    0.46
    ตัว
    0.45
     اع
    0.45
    ลัง
    0.45
    queros
    0.45
    Activations Density 0.001%

    No Known Activations