© 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. 101238
    Prev
    Next
    INDEX
    Explanations

    describing implications or versions

    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
     Prevent
    0.46
     Não
    0.46
    ید
    0.45
     endpoint
    0.45
     R
    0.45
     Tidak
    0.44
     Twins
    0.44
    s
    0.44
     E
    0.43
    ಗ್ಗೆ
    0.42
    POSITIVE LOGITS
     comentários
    0.48
     oscuridad
    0.48
     comentarios
    0.47
     آہ
    0.47
     abogados
    0.46
    コイル
    0.46
    Williams
    0.46
     pensamientos
    0.45
     afbeelding
    0.45
     собак
    0.45
    Activations Density 0.005%

    No Known Activations