© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 33158
    Prev
    Next
    INDEX
    Explanations

    regional distribution and entity comparisons

    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_31_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
    𝐞
    0.47
    <h3>
    0.46
     Parfum
    0.46
    ulação
    0.45
    দুর
    0.45
     openings
    0.43
    开放
    0.43
    谤
    0.43
    渀
    0.43
    <h5>
    0.43
    POSITIVE LOGITS
    Ball
    0.54
     восем
    0.52
     ball
    0.48
     ancest
    0.47
     дар
    0.46
     ዘዴ
    0.44
     dimensionless
    0.44
     eighth
    0.44
     בכ
    0.44
     đánh
    0.43
    Activations Density 0.000%

    No Known Activations