© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2338
    Prev
    Next
    INDEX
    Explanations

    with respect to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     from
    0.89
    *
    0.84
    '
    0.76
     here
    0.74
    的
    0.71
     to
    0.70
    ंमध्ये
    0.67
    ;
    0.65
    is
    0.64
     Ways
    0.64
    POSITIVE LOGITS
     regards
    1.63
     respect
    1.53
     regard
    1.52
     whom
    1.36
    drawn
    1.33
    standing
    1.30
    respect
    1.27
    inthe
    1.26
    whom
    1.25
     emphasis
    1.21
    Activations Density 0.769%

    No Known Activations