© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 664
    Prev
    Next
    INDEX
    Explanations

    explanations:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     servlet
    0.80
     halftone
    0.78
     endgame
    0.76
     cabo
    0.76
     sqm
    0.75
    <unused1074>
    0.73
     checksum
    0.73
     forklift
    0.72
    worthiness
    0.72
     relational
    0.72
    POSITIVE LOGITS
    <unused1443>
    1.01
    Ко
    0.73
    We
    0.72
    While
    0.70
    ↵↵
    0.69
    <eos>
    0.69
    Young
    0.68
    What
    0.67
    Being
    0.67
    По
    0.67
    Activations Density 0.095%

    No Known Activations