© 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. 4483
    Prev
    Next
    INDEX
    Explanations

    prefixes forming words

    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
    ‍♂
    1.12
    identité
    1.06
    ̣i
    1.02
    deos
    0.99
    unsaturated
    0.95
    dup
    0.95
    меня
    0.93
    voorbeeld
    0.92
    dik
    0.92
    numero
    0.92
    POSITIVE LOGITS
    queous
    1.64
    니아
    1.41
    亀
    1.39
     Hye
    1.36
    uture
    1.36
     Jeder
    1.33
     Ј
    1.32
    Ј
    1.32
     Ahora
    1.31
     Runnable
    1.31
    Activations Density 0.128%

    No Known Activations