© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 13831
    Prev
    Next
    INDEX
    Explanations

    table summarizing differences

    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
     father
    1.18
     next
    1.12
     heights
    1.12
     frequency
    1.11
     numbers
    1.10
     ஒருவர்
    1.10
     ‘
    1.08
    ocz
    1.06
     exact
    1.05
     tenth
    1.05
    POSITIVE LOGITS
    ViewHolder
    1.69
    Disha
    1.60
     aplikacji
    1.56
     कोरोना
    1.56
    ۂ
    1.55
     ఆఫ్
    1.54
    Defocused
    1.52
    botao
    1.52
    Emoji
    1.46
    वेस्ट
    1.45
    Activations Density 0.003%

    No Known Activations