© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11970
    Prev
    Next
    INDEX
    Explanations

    Best Choice

    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_7_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
    𝚞
    2.51
     scrollView
    2.32
    缎
    2.30
    ณฑ
    2.25
     déclaré
    2.22
     mingled
    2.22
    𝚊
    2.20
    ང་
    2.19
    
    2.16
     GSi
    2.15
    POSITIVE LOGITS
    alit
    3.14
    y
    2.91
    an
    2.88
    trom
    2.72
    া
    2.71
    ي
    2.70
    a
    2.65
    ing
    2.59
    en
    2.54
    erp
    2.54
    Activations Density 0.007%

    No Known Activations