© 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. 14355
    Prev
    Next
    INDEX
    Explanations

    languages and comparisons

    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
     tracker
    1.42
     morphism
    1.39
     calcular
    1.36
     clockRadius
    1.31
    ம்பர்
    1.31
     parametri
    1.31
     cohom
    1.30
    <unused258>
    1.29
     utilisez
    1.29
     edifici
    1.28
    POSITIVE LOGITS
    ,
    1.21
     ко
    1.14
    ..,
    0.98
    ,.
    0.98
    ،
    0.96
    oon
    0.92
    н
    0.92
    .,
    0.91
     on
    0.90
    fitting
    0.89
    Activations Density 0.002%

    No Known Activations