© 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. 14166
    Prev
    Next
    INDEX
    Explanations

    verify the authenticity

    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
    arily
    2.71
    reactivex
    2.65
    siniz
    2.62
     RtlOverlay
    2.49
    窕
    2.46
    ﺹ
    2.32
    राणिक
    2.25
    VCTargetsPath
    2.25
     beetje
    2.24
    de
    2.23
    POSITIVE LOGITS
    ه
    2.84
    ി
    2.84
    ம்
    2.82
    o
    2.73
    a
    2.71
    𝑚
    2.67
    i
    2.59
    oL
    2.57
    stroke
    2.55
    iota
    2.55
    Activations Density 0.013%

    No Known Activations