© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201713
    Prev
    Next
    INDEX
    Explanations

    geographic names and specific context words

    np_acts-logits-general · gemini-2.5-flash-lite

    reduce oxidative, improve fertility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ldots
    0.49
    m
    0.46
    aliana
    0.42
     مسؤول
    0.42
     Maur
    0.42
     opgenomen
    0.42
    iday
    0.41
     Ha
    0.41
     revoked
    0.41
     sacks
    0.40
    POSITIVE LOGITS
     abyss
    0.47
     வாயு
    0.45
     minum
    0.45
    foe
    0.45
    นำ
    0.43
    ͒
    0.42
     जिनसे
    0.42
     сильнее
    0.41
    Л
    0.41
     जिंदाबाद
    0.41
    Activations Density 0.003%

    No Known Activations