© 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. 12500
    Prev
    Next
    INDEX
    Explanations

    diagnostics and code syntax

    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
    boBox
    1.74
     excitations
    1.58
    <unused2186>
    1.48
    \}_{
    1.48
    ار
    1.48
    །
    1.48
     findAll
    1.47
     inescapable
    1.46
    rj
    1.45
     Lordships
    1.44
    POSITIVE LOGITS
    আ
    1.61
    ಭಾವ
    1.59
    এই
    1.58
    Τ
    1.57
    ভ
    1.54
    ์
    1.51
     SMEs
    1.47
     проводят
    1.47
     फिर
    1.44
    Unt
    1.43
    Activations Density 0.000%

    No Known Activations