© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10855
    Prev
    Next
    INDEX
    Explanations

    placeholders for dollar amounts or dates

    np_acts-logits-general · gemini-2.5-flash-lite

    defining placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    등
    0.39
    om
    0.38
    ','
    0.37
     gigs
    0.37
    logo
    0.37
    )【
    0.36
    https
    0.36
    TM
    0.36
     terrorists
    0.36
     condolences
    0.36
    POSITIVE LOGITS
     ______
    1.90
     _______
    1.88
     __________
    1.87
     ________
    1.84
     ____________
    1.84
     ____
    1.83
     _____________
    1.82
     _____
    1.81
     ___
    1.73
    ___________
    1.71
    Activations Density 0.060%

    No Known Activations