© 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. 8999
    Prev
    Next
    INDEX
    Explanations

    `main`, `world`, `<!DOCTYPE`

    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
    Pixels
    0.96
    Longitude
    0.90
    Quadrant
    0.88
     retribution
    0.88
     decided
    0.85
    緯
    0.85
    KeyPressed
    0.84
    reys
    0.83
     decisión
    0.82
    忌
    0.82
    POSITIVE LOGITS
     جعلی
    1.50
     pretends
    1.38
     pretending
    1.36
     Fake
    1.34
     pretended
    1.31
     거짓
    1.29
     fake
    1.27
     enga
    1.27
     bogus
    1.26
     disgu
    1.24
    Activations Density 0.299%

    No Known Activations