© 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. 31962
    Prev
    Next
    INDEX
    Explanations

    crisis, sector, apocalyptic, product

    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
     '%'
    0.50
    NESDAY
    0.50
     NuGet
    0.48
     INCLUDING
    0.48
     kWh
    0.47
     Thrift
    0.47
     Petitioner
    0.47
     Strength
    0.46
     Departments
    0.46
     Tianjin
    0.46
    POSITIVE LOGITS
    Reg
    0.49
    ق
    0.46
    ذ
    0.44
    hubungan
    0.44
    功能
    0.42
    erg
    0.42
    É
    0.42
     vivere
    0.42
    레
    0.41
     الذ
    0.41
    Activations Density 0.000%

    No Known Activations