© 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. 243
    Prev
    Next
    INDEX
    Explanations

    i followed by punctuation or code

    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
    are
    0.80
    d
    0.69
     plain
    0.67
     seemingly
    0.64
     probable
    0.61
     IMO
    0.60
     hypot
    0.59
     aren
    0.59
     are
    0.59
     presum
    0.59
    POSITIVE LOGITS
    roquois
    1.24
    çin
    1.08
    спользование
    1.03
    RELAND
    0.95
    ̇
    0.88
    ridium
    0.87
    ota
    0.86
    дентифика
    0.85
    спользова
    0.84
    Phones
    0.83
    Activations Density 0.496%

    No Known Activations