© 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. 12252
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     х
    2.80
     llegado
    2.74
    Т
    2.71
    Об
    2.61
    Depuis
    2.59
    }=
    2.35
     sib
    2.34
    Х
    2.34
    ță
    2.33
     dėl
    2.29
    POSITIVE LOGITS
    ו
    4.86
    d
    4.56
    e
    3.82
    a
    3.51
    т
    3.44
    و
    3.41
    r
    3.40
    ت
    3.36
    р
    3.36
    excluding
    3.34
    Activations Density 0.032%

    No Known Activations