© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5708
    Prev
    Next
    INDEX
    Explanations

    Smithsonian science articles

    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
     via
    0.69
     so
    0.67
     behind
    0.66
     their
    0.64
     der
    0.64
     i
    0.63
     being
    0.63
    ु
    0.62
     gifted
    0.61
     either
    0.61
    POSITIVE LOGITS
     Economía
    0.91
    ጺ
    0.86
    យ៉
    0.85
    频谱
    0.83
     ആരാധ
    0.82
    elementProp
    0.82
    ontan
    0.81
    ঞ্জাম
    0.81
    යක
    0.80
    Ȼ
    0.80
    Activations Density 0.008%

    No Known Activations