© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4298
    Prev
    Next
    INDEX
    Explanations

    Image, caption, visual

    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
    viving
    0.89
    etrics
    0.89
    :',
    0.87
    ities
    0.85
    :")
    0.84
    :",
    0.80
    :')
    0.78
    urer
    0.78
     wrenches
    0.78
    :\
    0.78
    POSITIVE LOGITS
    Image
    1.92
    Message
    1.90
    Download
    1.76
    图片
    1.72
     Image
    1.71
    Caption
    1.69
    image
    1.66
    Visual
    1.65
     пресс
    1.65
    При
    1.65
    Activations Density 0.082%

    No Known Activations