© 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. 342
    Prev
    Next
    INDEX
    Explanations

    I understand you're

    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
     Mut
    0.59
     Nested
    0.54
     Wings
    0.51
     চিক
    0.50
     having
    0.49
    =")"
    0.48
     Carbide
    0.48
     imati
    0.48
     Mutant
    0.47
    having
    0.46
    POSITIVE LOGITS
    밝
    0.66
     искусства
    0.58
     triumphant
    0.57
     tandis
    0.55
     dazzling
    0.54
     prosperous
    0.52
     بينما
    0.52
     prosa
    0.52
     shockingly
    0.52
    Después
    0.51
    Activations Density 0.400%

    No Known Activations