© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110227
    Prev
    Next
    INDEX
    Explanations

    initial actions, domestic, security, platforms

    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
    Полу
    0.50
    Анд
    0.46
    ٧
    0.46
    Те
    0.45
    क्षिक
    0.45
    etok
    0.45
    鋆
    0.45
    க்குப்
    0.44
    ዩ
    0.44
    ٨
    0.44
    POSITIVE LOGITS
    ’
    0.52
     umet
    0.46
     meri
    0.44
     ration
    0.42
     tissues
    0.42
     miesto
    0.42
     perc
    0.41
     flamenco
    0.41
     chem
    0.41
     hawk
    0.41
    Activations Density 0.004%

    No Known Activations