© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 53371
    Prev
    Next
    INDEX
    Explanations

    hypothetical explanations or implications

    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
    а
    0.51
    ilgan
    0.48
     пе
    0.46
     п
    0.45
    и
    0.44
     необы
    0.43
     the
    0.42
    the
    0.42
    О
    0.42
    acion
    0.42
    POSITIVE LOGITS
     suburbs
    0.42
     لدينا
    0.42
    ത്തേക്ക്
    0.42
     sewing
    0.40
     makeover
    0.40
     Secretaries
    0.39
    我們會
    0.39
     renovations
    0.39
     Sewer
    0.38
     budete
    0.38
    Activations Density 0.002%

    No Known Activations