© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7436
    Prev
    Next
    INDEX
    Explanations

    vitamin D deficiency

    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_22_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
    alya
    1.01
    рья
    0.98
     любить
    0.91
    tem
    0.89
     пів
    0.87
     наве
    0.87
    ренко
    0.85
    춧
    0.85
     associate
    0.85
    association
    0.85
    POSITIVE LOGITS
    <0x8A>
    1.45
     conversational
    1.18
    癥
    1.13
    स्ट्रेट
    0.99
    मूलन
    0.97
     getUser
    0.95
     crucially
    0.93
     Chord
    0.93
     filosóf
    0.92
     wasnt
    0.91
    Activations Density 0.002%

    No Known Activations