© 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. 99366
    Prev
    Next
    INDEX
    Explanations

    trouble, hour, that

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

    context words

    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
     KAR
    0.47
    ل
    0.45
    を使った
    0.45
    YLE
    0.45
    డింది
    0.45
     battled
    0.43
     দুটি
    0.42
     CAR
    0.42
    エース
    0.42
    尼亚克
    0.41
    POSITIVE LOGITS
    Hydrochloride
    0.50
     янва
    0.48
    но
    0.48
    reo
    0.47
    y
    0.46
    रोना
    0.46
    e
    0.46
    ppsala
    0.45
     hanger
    0.44
    ውነ
    0.43
    Activations Density 0.000%

    No Known Activations