© 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. 99651
    Prev
    Next
    INDEX
    Explanations

    language conjunction followed by context word

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

    phrases about how to prevent or do something

    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
     утро
    0.47
     лучших
    0.47
     ডো
    0.46
    getSign
    0.45
    ků
    0.45
     формата
    0.45
     ремонта
    0.44
    封
    0.44
    kých
    0.44
    ícul
    0.44
    POSITIVE LOGITS
    sonsten
    0.46
     statt
    0.44
    /@
    0.42
     stack
    0.41
    otope
    0.41
     sedang
    0.40
     chitin
    0.40
    🎤
    0.40
    Type
    0.40
     wichtig
    0.40
    Activations Density 0.000%

    No Known Activations