© 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. 9-GEMMASCOPE-2-RES-262K
    7. 12470
    Prev
    Next
    INDEX
    Explanations

    flip; 3x3 grids; batches

    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_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    (())
    1.16
    ტი
    1.15
    haben
    1.12
     lze
    1.11
    ່ວນ
    1.07
    ("-"*
    1.07
    erer
    1.05
    atives
    1.04
    ιδ
    1.04
     forth
    1.04
    POSITIVE LOGITS
    𝙉
    1.40
    𝐍
    1.37
     notorious
    1.31
    дцать
    1.29
    relay
    1.28
     sintered
    1.27
    𝙍
    1.26
     resorted
    1.25
     infamous
    1.24
     rover
    1.24
    Activations Density 0.002%

    No Known Activations