© 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. 98420
    Prev
    Next
    INDEX
    Explanations

    simplified unicorn

    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
    orben
    0.42
    annotation
    0.40
    Georges
    0.39
    white
    0.39
    恐
    0.39
     Og
    0.38
    כ
    0.38
    possessed
    0.38
    grey
    0.38
    ☎
    0.38
    POSITIVE LOGITS
    槛
    0.40
    vät
    0.39
     Easier
    0.38
     देता
    0.38
     Twilight
    0.37
    នុស្ស
    0.36
     Thanksgiving
    0.36
    ailles
    0.36
     publicó
    0.35
    ंव
    0.35
    Activations Density 0.001%

    No Known Activations