© 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. 44753
    Prev
    Next
    INDEX
    Explanations

    Fort San Pedro, Europe, animals

    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
     tubig
    0.45
     Dylan
    0.45
     dihydro
    0.45
     Investig
    0.45
     Chimie
    0.44
    궪
    0.44
     شیمی
    0.44
     Dioxide
    0.43
     methylation
    0.41
    抿
    0.41
    POSITIVE LOGITS
    Israel
    0.53
    Turkey
    0.51
    any
    0.50
    rak
    0.46
    you
    0.46
    по
    0.45
    Spain
    0.45
    कु
    0.44
    p
    0.44
    à
    0.44
    Activations Density 0.006%

    No Known Activations