© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52956
    Prev
    Next
    INDEX
    Explanations

    //, is there, a, or, yo, =

    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
    Imaging
    0.49
     Нет
    0.47
    *",
    0.46
    sol
    0.45
     Ю
    0.45
     Rakyat
    0.44
     এসব
    0.44
     definiert
    0.44
     張
    0.44
     দৃষ্টিভ
    0.44
    POSITIVE LOGITS
    的上
    0.45
     superman
    0.43
     getMax
    0.41
    用の
    0.39
    鳝
    0.39
     tedious
    0.39
     echoing
    0.39
     ditches
    0.39
     jPanel
    0.39
     drainage
    0.38
    Activations Density 0.001%

    No Known Activations