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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2579
    Prev
    Next
    INDEX
    Explanations

    reverse or invert

    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
    น
    3.14
    y
    3.02
    ا
    2.94
    ে
    2.93
    o
    2.87
    る
    2.86
    ために
    2.85
    י
    2.84
    ي
    2.81
    न
    2.77
    POSITIVE LOGITS
    琶
    2.44
    道府県
    2.34
    JsonProperty
    2.20
    дцать
    2.11
    playerId
    2.02
    器的
    1.97
    匐
    1.96
     линию
    1.96
    俐
    1.95
    蟀
    1.95
    Activations Density 0.427%

    No Known Activations