© 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. 36532
    Prev
    Next
    INDEX
    Explanations

    code or promo

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

    demonstrating how hate speech functions

    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
    ên
    0.47
    ȋ
    0.44
    getC
    0.41
    <0x89>
    0.39
    ってる
    0.38
    ครั้ง
    0.37
    î
    0.37
    ','
    0.37
    ð
    0.37
    ṕ
    0.37
    POSITIVE LOGITS
     isom
    0.46
     ischemia
    0.44
     magnitudes
    0.43
     赵
    0.42
     traum
    0.42
     entour
    0.41
     angu
    0.40
     transgress
    0.39
     unix
    0.39
     stratosphere
    0.39
    Activations Density 0.000%

    No Known Activations