© 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. 7-GEMMASCOPE-2-RES-16K
    7. 185
    Prev
    Next
    INDEX
    Explanations

    ; followed by newline

    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
    ete
    1.39
    closest
    1.19
    fulness
    1.17
    𝘀
    1.13
    ureate
    1.09
    كلة
    1.09
    eted
    1.08
    board
    1.05
     reckon
    1.05
    setBadgeText
    1.03
    POSITIVE LOGITS
    s
    2.34
    sion
    1.74
    т
    1.73
    ség
    1.65
    sens
    1.65
    sap
    1.58
    sü
    1.57
    ्स
    1.56
    sik
    1.55
    sons
    1.55
    Activations Density 0.186%

    No Known Activations