© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14888
    Prev
    Next
    INDEX
    Explanations

    extensions, upgrade, configuration, investment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     puno
    1.14
    kimi
    1.13
    ের
    1.09
    uko
    1.08
    eldo
    1.08
     pou
    1.08
    ırs
    1.07
     $(<
    1.06
     tots
    1.06
    ({\
    1.06
    POSITIVE LOGITS
     Carmel
    1.17
     longevity
    1.15
     Horace
    1.14
     Amarillo
    1.13
    ことで
    1.10
     Laguna
    1.09
    カル
    1.08
     Cali
    1.08
     Aurora
    1.08
     Bell
    1.08
    Activations Density 0.000%

    No Known Activations