© 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. 83741
    Prev
    Next
    INDEX
    Explanations

    scale, RNA, Modi, Revolt

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

    contrast or exception

    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
     vü
    0.46
     дизайне
    0.44
     Deutschlands
    0.44
    Countries
    0.43
    Ph
    0.43
     समायोजित
    0.42
    洳
    0.42
     Bewertungen
    0.42
     تمہیں
    0.42
    ancement
    0.42
    POSITIVE LOGITS
    탉
    0.46
     insists
    0.44
     सुपारी
    0.44
     fragile
    0.42
     wasteful
    0.41
    alos
    0.40
    უნქ
    0.40
     persists
    0.40
    뜩
    0.40
     tradicional
    0.40
    Activations Density 0.001%

    No Known Activations