© 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. 12177
    Prev
    Next
    INDEX
    Explanations

    Japanese anime, PDA, asset

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

    common sentence completions

    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
    تباين
    0.57
     särsk
    0.55
     punctato
    0.55
     కీలక
    0.55
    듦
    0.54
     основные
    0.54
    臨床
    0.54
    頜
    0.54
    關於
    0.54
    さまざまな
    0.54
    POSITIVE LOGITS
     asshole
    0.92
     fucking
    0.92
     pokemon
    0.88
     Pokemon
    0.87
     fuck
    0.85
     shitty
    0.84
     nigga
    0.83
     haters
    0.83
     Fuck
    0.82
     joke
    0.81
    Activations Density 0.127%

    No Known Activations