© 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. 14562
    Prev
    Next
    INDEX
    Explanations

    inhale

    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
    蟀
    2.71
    ledi
    2.61
     enne
    2.55
    𝘂
    2.55
    LowerCase
    2.52
    θηκε
    2.42
    θηκαν
    2.40
    ties
    2.39
     ràng
    2.38
    𝐮
    2.29
    POSITIVE LOGITS
    ed
    3.47
    ে
    3.42
    is
    3.11
    aul
    2.98
    eck
    2.98
    ো
    2.93
    ので
    2.93
    eer
    2.92
    aar
    2.91
    edas
    2.87
    Activations Density 0.012%

    No Known Activations