© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125111
    Prev
    Next
    INDEX
    Explanations

    agreed to which you

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

    YouTube, paper, adventure

    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_31_width_262k_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
    Z
    0.51
    script
    0.50
    s
    0.48
    窮
    0.48
    篇
    0.47
    e
    0.46
    ein
    0.46
    A
    0.44
    しまう
    0.44
    mak
    0.43
    POSITIVE LOGITS
     Cycles
    0.49
     AGE
    0.48
    रानी
    0.46
     为
    0.46
     actomyosin
    0.46
    鲵
    0.44
     মু
    0.44
     sensors
    0.44
     TokenType
    0.43
     Appointments
    0.43
    Activations Density 0.001%

    No Known Activations