© 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. 14519
    Prev
    Next
    INDEX
    Explanations

    camera, lens, photography

    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
    ta
    2.33
    atement
    2.25
     ABI
    2.25
     ghostly
    2.20
     spooky
    2.20
    忑
    2.18
    笄
    2.17
    ٰ
    2.15
     (“
    2.14
     manut
    2.13
    POSITIVE LOGITS
    ing
    2.92
    ும்
    2.82
     gió
    2.75
    annten
    2.74
    κι
    2.63
    erin
    2.60
    िंग
    2.51
    orys
    2.51
    ್ಣ
    2.50
    estimators
    2.49
    Activations Density 0.011%

    No Known Activations