© 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. 251012
    Prev
    Next
    INDEX
    Explanations

    translation software libraries experience

    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
    ଉ
    0.45
    言語
    0.44
     Funktionen
    0.43
    スキル
    0.43
     кін
    0.43
    を一
    0.43
    权力
    0.42
    怪
    0.42
    牠
    0.42
    所謂
    0.42
    POSITIVE LOGITS
     deo
    0.49
     tour
    0.45
    ،
    0.45
     toast
    0.44
    hôte
    0.44
    scn
    0.44
    actos
    0.43
     TOUR
    0.43
    toast
    0.43
    intos
    0.43
    Activations Density 0.001%

    No Known Activations