© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11826
    Prev
    Next
    INDEX
    Explanations

    pre-trained, existing, or other components

    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
     --
    1.07
     —
    0.99
     -
    0.95
     absolutely
    0.86
     |
    0.84
     ALSO
    0.83
     ---
    0.78
     –
    0.76
     ـ
    0.75
    View
    0.73
    POSITIVE LOGITS
     whereas
    1.82
     sedangkan
    1.78
     অপরদিকে
    1.72
    whereas
    1.70
     tandis
    1.67
    /;
    1.60
    %；
    1.57
    ’;
    1.52
    %;
    1.51
    ；
    1.49
    Activations Density 0.299%

    No Known Activations