© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32914
    Prev
    Next
    INDEX
    Explanations

    not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     categoría
    0.43
     categoria
    0.42
     category
    0.41
    ிருப்பது
    0.38
    สัตว์
    0.38
    उत्तर
    0.37
    ;
    0.37
    壌
    0.37
     ammo
    0.36
     catégorie
    0.36
    POSITIVE LOGITS
     not
    0.52
     ничего
    0.52
     neither
    0.49
     rien
    0.47
     guère
    0.46
     decât
    0.45
    也沒有
    0.44
     NOTHING
    0.44
    碐
    0.42
     NOT
    0.41
    Activations Density 0.000%

    No Known Activations