© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 223699
    Prev
    Next
    INDEX
    Explanations

    attached homes and internet

    np_acts-logits-general · gemini-2.5-flash-lite

    formal workplaces or parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muscat
    0.50
    вање
    0.47
    Tatar
    0.46
    Є
    0.46
    يسي
    0.46
    ן
    0.45
     Musica
    0.45
    регистри
    0.45
     発
    0.44
    אי
    0.44
    POSITIVE LOGITS
     assemblages
    0.52
     epochs
    0.52
    ocam
    0.52
     Address
    0.48
    ouflage
    0.47
     মিটিং
    0.47
     fields
    0.47
    舰
    0.46
     services
    0.45
     artifacts
    0.45
    Activations Density 0.001%

    No Known Activations