© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3947
    Prev
    Next
    INDEX
    Explanations

    knowledge cutoff date

    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_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     oldest
    0.71
     tenth
    0.69
     Tenth
    0.68
    昔
    0.68
    頃
    0.66
     mailed
    0.64
    UpdatedAt
    0.64
     prvi
    0.63
    Mirror
    0.62
    ponente
    0.62
    POSITIVE LOGITS
    ern
    0.74
    ្វ
    0.71
     adherence
    0.70
     hasard
    0.68
     adherent
    0.66
     adh
    0.66
    লা
    0.64
     উভয়
    0.63
    Ἠ
    0.63
    érables
    0.63
    Activations Density 0.126%

    No Known Activations