© 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. 1592
    Prev
    Next
    INDEX
    Explanations

    dialogue containing actions

    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
    POSTFIELDS
    1.42
     INSTITUTE
    1.40
     thuộc
    1.40
    numberOfRecords
    1.37
    ἁ
    1.35
     nonnegative
    1.33
    ').':
    1.33
     것으로
    1.33
    高品質
    1.32
    近年
    1.32
    POSITIVE LOGITS
     "
    2.12
     “
    2.05
    “
    1.98
     “‘
    1.95
    “-
    1.94
     Suddenly
    1.94
    Suddenly
    1.93
    "
    1.90
     "¿
    1.88
     "'
    1.87
    Activations Density 0.160%

    No Known Activations