© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1041
    Prev
    Next
    INDEX
    Explanations

    save the code

    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
     is
    3.23
    a
    3.08
     has
    3.04
     and
    3.02
     was
    2.98
    2
    2.94
    1
    2.94
     to
    2.83
    .
    2.79
    0
    2.75
    POSITIVE LOGITS
    𒀖
    3.45
    ఋతం
    3.43
     BusABC
    3.43
     cosidd
    3.42
    𒆤
    3.40
    𒅕
    3.39
    𒌵
    3.38
    𒁾
    3.37
    DUNLAND
    3.36
    Razibul
    3.36
    Activations Density 0.051%

    No Known Activations