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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 971
    Prev
    Next
    INDEX
    Explanations

    complex questions

    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_65k_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
    cand
    1.27
    myer
    1.09
    lof
    1.05
     *>(
    1.05
    coproteins
    1.04
    lattice
    1.03
    ,\
    1.02
    𝘮
    1.00
     \,
    0.99
    eal
    0.98
    POSITIVE LOGITS
     memastikan
    1.34
     Bisby
    1.30
     Massive
    1.24
    Lucky
    1.21
     Precious
    1.20
     Wooden
    1.20
     Accessed
    1.20
     profissionais
    1.18
    左右
    1.18
    ভাগে
    1.17
    Activations Density 0.002%

    No Known Activations