© 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. 212407
    Prev
    Next
    INDEX
    Explanations

    manufacturer

    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
     यस
    0.39
     Subsidi
    0.39
     Ô
    0.37
     ప్రకట
    0.37
     İli
    0.36
    తిక
    0.36
     עצ
    0.36
    列
    0.35
     Compat
    0.35
     trži
    0.35
    POSITIVE LOGITS
    drawer
    0.44
     agile
    0.39
    revolution
    0.38
     griff
    0.38
    ympathetic
    0.37
     StreamWriter
    0.36
    ukasz
    0.36
    urgery
    0.35
     epinephrine
    0.35
    Adr
    0.35
    Activations Density 0.000%

    No Known Activations