© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3064
    Prev
    Next
    INDEX
    Explanations

    the action token

    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_7_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
    řel
    2.82
    __(/*!
    2.79
    epage
    2.68
    trz
    2.65
    urent
    2.58
    upné
    2.57
    ding
    2.55
    geist
    2.54
    ZL
    2.54
    gut
    2.52
    POSITIVE LOGITS
    ر
    3.77
    н
    3.22
    ority
    3.21
    er
    3.16
    сь
    3.06
    ра
    3.02
     consequence
    2.94
    webtoken
    2.92
    ার
    2.86
    ன்
    2.84
    Activations Density 0.033%

    No Known Activations