© 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. 3739
    Prev
    Next
    INDEX
    Explanations

    referring to context

    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
     sekä
    1.30
    u
    1.29
    ˧
    1.26
     Reihe
    1.24
    arli
    1.23
    ließt
    1.22
     belg
    1.22
    geht
    1.21
    amal
    1.21
     etik
    1.21
    POSITIVE LOGITS
    撓
    1.06
    Vec
    1.03
    ֩
    1.03
    ೂರಿನ
    1.02
    矮
    1.02
     ና
    1.00
     told
    0.99
    воен
    0.95
    sizeof
    0.94
     heaviest
    0.93
    Activations Density 0.052%

    No Known Activations