© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4055
    Prev
    Next
    INDEX
    Explanations

    ability to find

    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
    /******/
    0.70
     behaved
    0.67
     होके
    0.67
    become
    0.65
     Became
    0.64
    పార్
    0.64
     behaving
    0.64
    رحله
    0.63
     занимается
    0.63
    吩
    0.62
    POSITIVE LOGITS
     find
    4.13
     found
    3.85
    find
    3.76
     finds
    3.72
     finding
    3.69
     Find
    3.62
    Find
    3.61
     encontrar
    3.52
    找到
    3.38
     Finding
    3.27
    Activations Density 0.313%

    No Known Activations