© 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. 162180
    Prev
    Next
    INDEX
    Explanations

    German words and concepts

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

    often, particularly, common, frequent

    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
    রেক
    0.48
     shifting
    0.46
     kampung
    0.45
     selfie
    0.45
     elegido
    0.45
     teaming
    0.45
    횡
    0.45
     לפי
    0.44
    ิต
    0.44
    מי
    0.44
    POSITIVE LOGITS
    örungen
    0.50
    ut
    0.47
    ø
    0.45
    pp
    0.45
     Änderungen
    0.45
    periode
    0.44
    ppet
    0.43
     Sammlung
    0.43
    z
    0.43
    tä
    0.43
    Activations Density 0.000%

    No Known Activations