© 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. 10228
    Prev
    Next
    INDEX
    Explanations

    US St Scoring purpose

    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
     まし
    1.32
     interpolate
    1.28
     町
    1.18
     faktisk
    1.18
     ショート
    1.18
     Method
    1.13
     まあ
    1.12
     왜
    1.12
     dimas
    1.12
     松
    1.11
    POSITIVE LOGITS
    Aaron
    1.06
    Organ
    1.03
    Attachments
    1.02
    álny
    1.02
    ệng
    1.01
    ⦿
    1.01
    oggi
    0.98
    Ens
    0.97
    Organiz
    0.97
    Ongoing
    0.97
    Activations Density 0.000%

    No Known Activations