© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10332
    Prev
    Next
    INDEX
    Explanations

    italian things and concepts

    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
    Negative Logits
    ιουργ
    2.89
     lineColorSpace
    2.76
    쌔
    2.65
     popOperand
    2.64
    preconnect
    2.61
    jsdel
    2.61
    ☬
    2.58
     +#+
    2.56
    ⤦
    2.53
    ΕΣ
    2.52
    POSITIVE LOGITS
    it
    2.23
    ,
    2.12
    ist
    2.03
    and
    2.03
     and
    2.02
     to
    1.91
    '
    1.88
    atis
    1.84
    -
    1.84
    et
    1.78
    Activations Density 0.103%

    No Known Activations