© 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. 109378
    Prev
    Next
    INDEX
    Explanations

    following bullet points

    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
     Closed
    0.43
    borough
    0.42
    採取
    0.42
     reject
    0.41
    縣
    0.41
    ឿង
    0.40
     purchaser
    0.40
     renovación
    0.40
    ranos
    0.39
     dailySales
    0.39
    POSITIVE LOGITS
    ීන්
    0.38
     Warcraft
    0.37
    等于
    0.36
    挍
    0.36
    yc
    0.34
    ীল
    0.34
    сни
    0.34
    лната
    0.34
     พระ
    0.34
    COMMIT
    0.34
    Activations Density 0.000%

    No Known Activations