© 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. 223163
    Prev
    Next
    INDEX
    Explanations

    six types

    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
     тебе
    0.42
    氵
    0.42
     authorisation
    0.41
    പൊ
    0.40
     Meinung
    0.38
    )#
    0.38
     jd
    0.37
    вна
    0.37
    どうしても
    0.36
     годи
    0.36
    POSITIVE LOGITS
     comedor
    0.45
     बैठने
    0.44
     Corresponding
    0.43
     বিশ্রাম
    0.42
     hangar
    0.40
     Focusing
    0.40
     HUB
    0.39
    十
    0.39
     Bicycle
    0.37
    Cycling
    0.37
    Activations Density 0.000%

    No Known Activations