© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6950
    Prev
    Next
    INDEX
    Explanations

    trigonometric-limits)

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     смогут
    0.94
     были
    0.93
    Params
    0.93
     на
    0.93
     убы
    0.92
     могут
    0.91
     тести
    0.89
     способны
    0.89
    ++)//
    0.89
     возможностей
    0.88
    POSITIVE LOGITS
     Electronic
    0.67
    无
    0.67
    ask
    0.66
    rick
    0.66
    Electronic
    0.65
     Asking
    0.65
     ask
    0.64
    esch
    0.63
     ασ
    0.63
     asking
    0.61
    Activations Density 0.021%

    No Known Activations