© 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. 234
    Prev
    Next
    INDEX
    Explanations

    direct contact, sales, or experience

    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
     pédicule
    1.62
     coseno
    1.52
    Bokeh
    1.52
     Bhagavato
    1.51
    údo
    1.48
    ুমাত্র
    1.48
     penerapan
    1.48
    㫙
    1.47
    の中心
    1.46
     nbfs
    1.46
    POSITIVE LOGITS
    iz
    1.20
    ized
    1.18
    izing
    1.15
    ised
    1.15
    化的
    1.13
     ‘
    1.13
    ization
    1.11
    izations
    1.09
    isation
    1.05
    i
    1.04
    Activations Density 6.839%

    No Known Activations