© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3748
    Prev
    Next
    INDEX
    Explanations

    Claro

    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
    ниш
    1.88
     bhas
    1.34
    миз
    1.34
    司令
    1.32
    անի
    1.31
     >;
    1.30
     nå
    1.30
    λεί
    1.30
    φε
    1.30
    젓
    1.29
    POSITIVE LOGITS
    idirectional
    1.17
     undirected
    0.96
    缛
    0.95
    litre
    0.91
     Rayleigh
    0.88
     fragmented
    0.82
    iliki
    0.82
     escrow
    0.81
     ETL
    0.81
    inhua
    0.81
    Activations Density 0.062%

    No Known Activations