© 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. 12434
    Prev
    Next
    INDEX
    Explanations

    breakdown of components or steps

    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
    ும்
    1.71
    ⎝
    1.59
    delicious
    1.56
    র
    1.51
    difficult
    1.49
    described
    1.49
    ০
    1.48
    د
    1.44
    ي
    1.42
    stuffs
    1.38
    POSITIVE LOGITS
     funzione
    1.46
    er
    1.38
    jenis
    1.38
     isomer
    1.36
     गत
    1.34
    ṣ
    1.33
     szervez
    1.32
     biasa
    1.30
     genotype
    1.30
    ük
    1.30
    Activations Density 0.040%

    No Known Activations