© 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. 17-GEMMASCOPE-2-RES-16K
    7. 5943
    Prev
    Next
    INDEX
    Explanations

    why you

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ચે
    0.86
    जन्य
    0.83
    اہم
    0.82
    ியின்
    0.81
     दिखे
    0.81
     Effectiveness
    0.80
     Экс
    0.80
    டியாக
    0.80
    됨
    0.80
     ఎలా
    0.79
    POSITIVE LOGITS
     couldn
    0.80
     vouloir
    0.78
     hiding
    0.74
    Ἀ
    0.71
    English
    0.70
     quitting
    0.69
    <unused1740>
    0.68
     plain
    0.68
    కాలు
    0.68
     quit
    0.67
    Activations Density 0.081%

    No Known Activations