© 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. 11530
    Prev
    Next
    INDEX
    Explanations

    get up and move

    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
     automático
    1.46
     contexto
    1.42
     примере
    1.36
     pacote
    1.36
    setCharacter
    1.35
    Ко
    1.35
     Использу
    1.34
    >$
    1.33
    し
    1.31
    调用
    1.31
    POSITIVE LOGITS
     scandalous
    1.47
     commendable
    1.46
     staggering
    1.43
     proclaiming
    1.43
     agonizing
    1.42
     gripping
    1.41
     proclaims
    1.41
     suffering
    1.39
     accusing
    1.38
     extraordinarily
    1.38
    Activations Density 0.002%

    No Known Activations