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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120700
    Prev
    Next
    INDEX
    Explanations

    medical advice, legislation, properties, languages, cases

    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/layer_40_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
     Involved
    0.47
     involved
    0.45
    involved
    0.40
    ុម
    0.39
    ษฐ
    0.38
    打了
    0.37
     sniping
    0.37
    ｔ
    0.37
    INSERT
    0.37
    fora
    0.37
    POSITIVE LOGITS
    ங்கி
    0.40
    ものを
    0.40
     weren
    0.39
     দীর্ঘ
    0.37
    ものは
    0.37
     शनिवार
    0.36
    ónimo
    0.36
     Polyg
    0.36
    <strong>
    0.36
     denen
    0.36
    Activations Density 0.000%

    No Known Activations