© 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. 132435
    Prev
    Next
    INDEX
    Explanations

    staff and power

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

    consent and violation

    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
    CTest
    0.47
    鈣
    0.43
     SELF
    0.42
     测试
    0.42
     দেবতার
    0.42
    屬
    0.42
    鸡
    0.42
    雞
    0.42
    獒
    0.42
    供應
    0.42
    POSITIVE LOGITS
    선
    0.52
    olding
    0.52
    regelen
    0.50
     staf
    0.46
    PerTrial
    0.46
    meed
    0.45
     ellipso
    0.45
     कार्यकर्ताओं
    0.44
     lesqu
    0.44
    viene
    0.44
    Activations Density 0.001%

    No Known Activations