© 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. 14372
    Prev
    Next
    INDEX
    Explanations

    complete solutions

    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
    ς
    3.78
    了
    3.56
    ु
    3.51
    nya
    3.40
    PlistBuddy
    3.33
    sene
    3.20
    dı
    3.09
    ों
    3.05
    ย
    2.94
    dě
    2.90
    POSITIVE LOGITS
    hension
    2.85
    찌
    2.80
    UR
    2.80
    றிய
    2.51
    lections
    2.46
    ptives
    2.38
    ibles
    2.32
     noten
    2.32
    __(/*!
    2.30
    त्मक
    2.30
    Activations Density 0.019%

    No Known Activations