Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2859
    Prev
    Next
    INDEX
    Explanations

    next number

    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
    ciation
    2.56
    swald
    2.25
    𝓱
    2.17
    σι
    2.17
    oramic
    2.16
    ὔ
    2.15
    σία
    2.13
    պ
    2.12
    핌
    2.11
    idefinite
    2.11
    POSITIVE LOGITS
    থেষ্ট
    2.58
    靼
    2.58
     amalgamation
    2.47
     retorted
    2.38
     Accumulated
    2.33
    ェ
    2.31
     amalgam
    2.31
    ous
    2.31
    াব্দ
    2.26
     Ecological
    2.25
    Activations Density 0.585%

    No Known Activations