© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5410
    Prev
    Next
    INDEX
    Explanations

    refine or narrow down further

    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
     Workshops
    1.21
     अगदी
    1.16
    ดี๋ยว
    1.15
    惬
    1.15
     Mixtures
    1.14
    ърква
    1.13
    aphazard
    1.12
    ដូច្ន
    1.12
    SPRAY
    1.11
    翛
    1.10
    POSITIVE LOGITS
     rec
    1.07
    したのは
    0.99
     lied
    0.96
     int
    0.96
     supposed
    0.95
     connot
    0.94
     dimension
    0.94
     len
    0.93
     ern
    0.93
     dating
    0.93
    Activations Density 0.175%

    No Known Activations