© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6502
    Prev
    Next
    INDEX
    Explanations

    echoed in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    incerely
    1.03
    temper
    0.98
    permitted
    0.86
    activity
    0.86
     ei
    0.82
    愉
    0.81
    允許
    0.79
    translated
    0.79
    flip
    0.78
    卽
    0.78
    POSITIVE LOGITS
     Jurisdiction
    1.98
     connaissance
    1.95
     nú
    1.90
    盾
    1.89
    inence
    1.88
     OBC
    1.88
    รู้จัก
    1.85
     NPA
    1.84
     NICKEL
    1.84
    อด
    1.83
    Activations Density 0.006%

    No Known Activations