© 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-16K
    7. 2729
    Prev
    Next
    INDEX
    Explanations

    defining aspects and restrictions

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     equivalently
    1.80
     както
    1.77
     alternatively
    1.62
     è
    1.59
     zumindest
    1.58
     incluso
    1.50
     conversely
    1.47
     proteinuria
    1.47
     é
    1.45
    вшись
    1.45
    POSITIVE LOGITS
    ]");
    1.50
    ]][
    1.37
    ]",
    1.36
    al
    1.36
    作用
    1.30
    ся
    1.19
    amp
    1.17
    \/
    1.16
    क्ष्म
    1.14
    -\
    1.12
    Activations Density 0.151%

    No Known Activations