© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 180
    Prev
    Next
    INDEX
    Explanations

    web and tech content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    7
    1.02
    5
    1.01
    6
    0.99
    줍니다
    0.97
    8
    0.97
     Moro
    0.95
    gt
    0.93
     Blender
    0.89
    بلا
    0.89
    MPT
    0.88
    POSITIVE LOGITS
     columnist
    0.87
    няў
    0.85
     implementing
    0.85
    емов
    0.83
    कक्ष
    0.82
     delivering
    0.81
    www
    0.80
     叶
    0.80
    edged
    0.80
    カム
    0.80
    Activations Density 0.088%

    No Known Activations