© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4814
    Prev
    Next
    INDEX
    Explanations

    leaning forward or on the floor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     содержания
    1.70
     günü
    1.67
     vols
    1.67
     내용은
    1.57
     hồn
    1.57
    dword
    1.56
    퀄
    1.56
    gün
    1.55
     redundancy
    1.54
    etés
    1.53
    POSITIVE LOGITS
    sliding
    1.23
     elektry
    1.21
    abst
    1.20
    swing
    1.18
     기울
    1.13
    Slides
    1.12
    ladies
    1.10
    Speaker
    1.10
    凳
    1.09
    chairs
    1.06
    Activations Density 0.050%

    No Known Activations