© 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. 26327
    Prev
    Next
    INDEX
    Explanations

    crusher price, catholic singles

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

    context window, attention mechanism

    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
    axanthin
    0.44
    ligence
    0.43
    atation
    0.43
    :
    0.42
     אי
    0.41
    ת
    0.40
    *
    0.40
    ت
    0.39
    probability
    0.38
    ל
    0.38
    POSITIVE LOGITS
     supérieurs
    0.45
     एक्ट्रेस
    0.44
    ഷേ
    0.44
     avenida
    0.43
     surtout
    0.42
     dziew
    0.42
    फ्रेंस
    0.42
    Соц
    0.42
     ámbitos
    0.42
    ocole
    0.41
    Activations Density 0.000%

    No Known Activations