© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    existence, identity, basic operations

    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
     najleps
    1.88
     lược
    1.87
    ストラ
    1.80
     arranges
    1.79
    κολ
    1.75
    ミリー
    1.72
     entrevistas
    1.69
    聪
    1.66
     største
    1.64
     lures
    1.64
    POSITIVE LOGITS
    landet
    2.01
     basic
    1.92
    identité
    1.91
    mate
    1.89
    LICENSE
    1.81
    SelfPermission
    1.75
    rinsic
    1.75
    assertTrue
    1.74
    Existence
    1.69
     موجوده
    1.69
    Activations Density 0.071%

    No Known Activations