© 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-16K
    7. 12705
    Prev
    Next
    INDEX
    Explanations

    German language or translations

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

    Deutsches, kein, keine, Kindern, Sprachen

    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_16k_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
    ቐ
    0.47
    ﾑ
    0.47
    Nc
    0.44
    Vc
    0.44
    φαι
    0.44
    kq
    0.43
    鉢
    0.43
    rw
    0.43
    SPE
    0.42
    வ்வேறு
    0.42
    POSITIVE LOGITS
     Deutsches
    0.65
     keine
    0.61
     Alta
    0.57
     Weitere
    0.55
     kein
    0.55
     Keine
    0.54
     Kindern
    0.53
     Sprachen
    0.52
     Deutscher
    0.52
     Autoren
    0.52
    Activations Density 0.002%

    No Known Activations