© 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. 14258
    Prev
    Next
    INDEX
    Explanations

    Haar Cascade Classifier, Angry Men, Dred Scott Decision

    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
     everywhere
    1.85
     almost
    1.67
     equivalents
    1.45
     instinct
    1.40
     nearly
    1.40
     domes
    1.38
     merely
    1.36
    -"
    1.34
     prospects
    1.33
    anians
    1.33
    POSITIVE LOGITS
    Bộ
    2.84
    ء
    2.61
    ğinin
    2.56
    𒆜
    2.51
    Título
    2.50
    ඪ
    2.47
    ڑے
    2.45
    Tổng
    2.40
    دع
    2.39
     poč
    2.39
    Activations Density 0.000%

    No Known Activations