© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7409
    Prev
    Next
    INDEX
    Explanations

    arm circles time durations

    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
    atically
    1.22
    足以
    1.19
    谐
    1.18
    هُ
    1.17
    вали
    1.17
    دق
    1.16
    츰
    1.16
    碗
    1.16
    ẳ
    1.15
    োট
    1.15
    POSITIVE LOGITS
     statunitense
    1.32
     southern
    1.31
     ministries
    1.29
     northern
    1.25
     europea
    1.23
     Manuscripts
    1.23
     sociedade
    1.21
     royals
    1.20
     países
    1.17
     Ministries
    1.16
    Activations Density 0.021%

    No Known Activations