© 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. 9050
    Prev
    Next
    INDEX
    Explanations

    class selector or programming class

    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
    𝙩
    2.55
    ́t
    2.37
    אל
    2.32
    ータ
    2.30
    uição
    2.26
    鈞
    2.23
    𝙫
    2.22
    一股
    2.18
    та
    2.13
     túl
    2.13
    POSITIVE LOGITS
    rooms
    3.17
    靼
    3.06
    ++++
    2.67
    渫
    2.59
    തല്ല
    2.55
    ो
    2.54
    locker
    2.49
    ︎
    2.49
    CONH
    2.49
    rimazole
    2.49
    Activations Density 0.516%

    No Known Activations