© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6850
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by types

    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_12_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
     morn
    1.71
     morning
    1.67
     onward
    1.59
     afternoon
    1.52
    ===============
    1.52
     Weather
    1.48
     night
    1.47
    createTextNode
    1.45
     Decision
    1.45
     Round
    1.44
    POSITIVE LOGITS
    sites
    2.73
    ร้าย
    2.59
    ی
    2.52
    siz
    2.48
    оло
    2.43
    ես
    2.40
     увиде
    2.38
    DEFGHIJKLMNOP
    2.37
    وڑا
    2.36
    یف
    2.33
    Activations Density 0.030%

    No Known Activations