© 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. 3350
    Prev
    Next
    INDEX
    Explanations

    measurements

    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
     leaps
    1.31
    ď
    1.30
     hop
    1.19
    anded
    1.11
     HOP
    1.11
     estre
    1.11
     jumps
    1.05
     nature
    1.05
    咪
    1.04
    estone
    1.01
    POSITIVE LOGITS
    ridine
    1.65
    SHO
    1.65
    촬
    1.64
    年始
    1.61
    rake
    1.60
    trk
    1.56
    fonos
    1.55
    cutaneous
    1.55
    rakes
    1.53
     notícias
    1.53
    Activations Density 0.024%

    No Known Activations