© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5325
    Prev
    Next
    INDEX
    Explanations

    breakdown of topics

    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
     -
    0.66
     In
    0.62
     (
    0.60
    re
    0.60
     it
    0.59
     or
    0.58
     in
    0.58
     _
    0.57
     –
    0.56
     membayar
    0.56
    POSITIVE LOGITS
     aimed
    1.04
     commenced
    1.01
    畛
    1.00
     ব্যাবস্থা
    0.99
     nuest
    0.98
     devised
    0.97
    迨
    0.97
    इंद
    0.95
     wasnt
    0.94
     primaryLanguage
    0.94
    Activations Density 0.103%

    No Known Activations