© 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. 11740
    Prev
    Next
    INDEX
    Explanations

    `st`, `as`, `fields`, `factories`, `hearing`

    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
     noh
    0.71
     adopt
    0.64
     ‘
    0.64
     Lovers
    0.64
     ভালোবাস
    0.62
     पांव
    0.62
     love
    0.61
     “
    0.61
     Bub
    0.59
     favoured
    0.58
    POSITIVE LOGITS
    ozat
    0.95
    iót
    0.90
    ewski
    0.88
    ventional
    0.85
    ilità
    0.83
    繧
    0.82
    aterial
    0.81
    atsby
    0.80
    筮
    0.80
    médiaire
    0.79
    Activations Density 0.000%

    No Known Activations