© 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. 150800
    Prev
    Next
    INDEX
    Explanations

    tango shows

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

    deceptive You or Lann

    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
    Bhar
    0.46
    Carpenter
    0.44
    "?>
    0.43
    ซิ
    0.43
    Bounding
    0.42
    帆
    0.42
    Punk
    0.41
    BRIDGE
    0.41
    בר
    0.41
    Sail
    0.41
    POSITIVE LOGITS
     yaşı
    0.55
     فرمایا
    0.53
    <unused2115>
    0.52
     yaşam
    0.50
     وط
    0.49
     நொ
    0.49
     verilen
    0.47
     निशान
    0.46
     شكل
    0.46
    防御
    0.46
    Activations Density 0.000%

    No Known Activations