© 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. 12512
    Prev
    Next
    INDEX
    Explanations

    tools, tokenizers

    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
     diri
    1.44
    ف
    1.34
    ною
    1.29
    ве
    1.27
     largement
    1.24
     choline
    1.24
     vra
    1.22
     togel
    1.21
    со
    1.19
    物の
    1.18
    POSITIVE LOGITS
    க்
    1.85
    centaje
    1.78
    কারী
    1.65
    ర్
    1.65
     قرآن
    1.64
    què
    1.63
    俎
    1.62
    রত
    1.62
     indentation
    1.61
    রুখ
    1.58
    Activations Density 0.000%

    No Known Activations