© 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. 208543
    Prev
    Next
    INDEX
    Explanations

    take on, strategy, many

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

    but is

    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
     swój
    0.49
     svůj
    0.48
     свой
    0.47
    ь
    0.46
    </em>
    0.45
     fasted
    0.44
     leapt
    0.44
     svog
    0.43
     svoje
    0.43
     igjen
    0.43
    POSITIVE LOGITS
    ॉम
    0.55
     聞い
    0.55
    ቃዎች
    0.52
    scratch
    0.50
    correct
    0.49
    incorrect
    0.47
     書い
    0.46
     компанией
    0.45
    mathemat
    0.44
    $\--
    0.44
    Activations Density 0.002%

    No Known Activations