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. 3210
    Prev
    Next
    INDEX
    Explanations

    cloud computing and infrastructure

    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
    ه
    2.59
    ष्‍ट्र
    2.40
    携帯
    2.36
    Ꮳ
    2.18
    <unused2116>
    2.18
    çal
    2.12
    Pup
    2.12
    งาม
    2.06
    ugeot
    2.04
    xes
    2.03
    POSITIVE LOGITS
     Managed
    1.96
    𝘂
    1.88
    DOCTYPE
    1.87
    ׁ
    1.87
     nutri
    1.83
    वला
    1.75
     seid
    1.74
     pu
    1.72
    macht
    1.71
    ের
    1.71
    Activations Density 0.924%

    No Known Activations