© 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-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12119
    Prev
    Next
    INDEX
    Explanations

    believe in dreams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vững
    0.77
     Nahrung
    0.74
     Mercado
    0.69
     настоящий
    0.69
    互联网
    0.66
     médecine
    0.63
    厷
    0.62
     véritables
    0.61
    շ
    0.61
     금융
    0.61
    POSITIVE LOGITS
    Tuple
    0.75
     SOME
    0.73
    members
    0.71
    &&
    0.68
    ﺲ
    0.68
     &&
    0.66
    deleteAll
    0.65
    Backup
    0.64
    illées
    0.64
    majority
    0.64
    Activations Density 0.015%

    No Known Activations