© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    how youAndroid Java Studio

    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
    au
    1.24
     s
    1.23
     f
    1.21
    SSS
    1.20
    itals
    1.18
    op
    1.13
    ali
    1.13
     v
    1.12
    NT
    1.11
    U
    1.09
    POSITIVE LOGITS
    یه
    1.43
    𝓎
    1.37
    katore
    1.36
    pathi
    1.34
    㼛
    1.34
    .|__
    1.33
     considérer
    1.32
     पड़े
    1.32
    stufe
    1.31
     społec
    1.30
    Activations Density 0.000%

    No Known Activations