© 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. 1120
    Prev
    Next
    INDEX
    Explanations

    element to find

    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
     continental
    1.28
    <em>
    1.26
     disproportion
    1.20
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    1.17
     périphérique
    1.16
     marshmallow
    1.15
     displacement
    1.13
     multiple
    1.08
     circular
    1.08
     emplacement
    1.07
    POSITIVE LOGITS
    ↵
    2.90
    
    2.77
    ‬
    2.71
    <end_of_image>
    2.43
     Букмекердик
    2.19
     Букмекерлер
    2.16
    雰
    2.16
     ‫
    2.11
     andRow
    2.10
    ‬‬
    2.08
    Activations Density 3.502%

    No Known Activations