© 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. 4212
    Prev
    Next
    INDEX
    Explanations

    foreign words and numbers

    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
    amor
    1.57
     Syndicate
    1.53
     Synd
    1.50
    ************/
    1.49
    ấn
    1.47
     edificios
    1.47
     Soa
    1.45
    abban
    1.44
    <0xBC>
    1.43
     Monsters
    1.43
    POSITIVE LOGITS
    interpre
    1.07
    WAM
    1.05
    WUE
    1.03
    KIA
    0.98
    Present
    0.90
    interpretation
    0.88
     Interpre
    0.86
    OTOS
    0.85
    INIS
    0.84
    NAC
    0.84
    Activations Density 0.011%

    No Known Activations