© 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. 24494
    Prev
    Next
    INDEX
    Explanations

    Poo Big, Return To Office, Report, plates, iao

    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
     tumult
    0.42
     ponte
    0.41
     tầm
    0.39
     добы
    0.36
     ru
    0.35
    mapKey
    0.35
     shuttle
    0.35
    渴
    0.35
    wij
    0.34
     banca
    0.34
    POSITIVE LOGITS
    医
    0.41
     अद्भ
    0.39
    ্ন
    0.38
    Pré
    0.38
     ምር
    0.38
    !।
    0.37
     Brick
    0.36
    טר
    0.36
     Himself
    0.36
    brick
    0.36
    Activations Density 0.001%

    No Known Activations