© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13440
    Prev
    Next
    INDEX
    Explanations

    questions about why or what

    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
    ších
    1.67
    гали
    1.45
    wał
    1.44
    يق
    1.44
    ząt
    1.43
    zać
    1.41
    rägt
    1.41
    ₁.
    1.39
    ściej
    1.38
    هش
    1.38
    POSITIVE LOGITS
     IMO
    1.34
     terrific
    1.32
     abbey
    1.25
     darling
    1.25
     adorable
    1.22
     cute
    1.21
     intrepid
    1.21
     imo
    1.20
     哦
    1.18
     IMHO
    1.15
    Activations Density 0.014%

    No Known Activations