© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1076
    Prev
    Next
    INDEX
    Explanations

    without being

    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_65k_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
     (
    0.80
    ’
    0.67
    /
    0.64
    uh
    0.63
    (
    0.63
    esh
    0.63
    era
    0.62
    –
    0.61
    -
    0.60
    ‘
    0.60
    POSITIVE LOGITS
     mencegah
    1.37
     achieve
    1.35
     attain
    1.34
     éviter
    1.31
    更好地
    1.31
     alleviate
    1.30
     prevenir
    1.29
     adegu
    1.28
     attaining
    1.27
     garantir
    1.27
    Activations Density 1.929%

    No Known Activations