© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 647
    Prev
    Next
    INDEX
    Explanations

    here's the start of an explanation

    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
     FIXME
    0.99
     នៅ
    0.98
    ύ
    0.95
    гато
    0.92
    हाँ
    0.91
    ціона
    0.90
     asemenea
    0.90
     späteren
    0.90
    हां
    0.89
     ይህም
    0.88
    POSITIVE LOGITS
    fordshire
    1.38
     is
    1.24
     are
    1.10
    து
    1.02
    on
    1.00
    inafter
    1.00
     what
    0.98
    저
    0.95
    what
    0.93
     sono
    0.93
    Activations Density 0.194%

    No Known Activations