© 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. 14649
    Prev
    Next
    INDEX
    Explanations

    risks and impact analysis

    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
     indicó
    1.55
    ؛
    1.46
    ática
    1.42
    áy
    1.40
    ){}^
    1.39
     destacó
    1.39
     explicó
    1.39
    átor
    1.39
    <unused1325>
    1.37
     vantagem
    1.36
    POSITIVE LOGITS
    ที่เรา
    0.87
     ourselves
    0.84
     fish
    0.78
    自分が
    0.75
     gonna
    0.75
     pillar
    0.74
     things
    0.74
     everything
    0.74
    i
    0.74
     signs
    0.71
    Activations Density 0.011%

    No Known Activations