© 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. 286
    Prev
    Next
    INDEX
    Explanations

    css properties

    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
    И
    1.54
    3
    1.47
    2
    1.45
    少し
    1.43
    Д
    1.43
    Oh
    1.40
    No
    1.38
    1
    1.38
    NO
    1.38
    А
    1.38
    POSITIVE LOGITS
     pertain
    2.16
     govern
    2.05
     ϕ
    2.02
     Φ
    2.00
     (§
    1.89
     coherent
    1.87
     perfor
    1.87
     για
    1.86
     pertains
    1.86
     φ
    1.85
    Activations Density 0.158%

    No Known Activations