© 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. 145651
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific nouns

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

    hackathon ideas

    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
     Khartoum
    0.45
     Courts
    0.45
     Задача
    0.45
     Está
    0.45
    씨
    0.45
     ავ
    0.44
     Mog
    0.44
    є
    0.44
     Кур
    0.43
     வில்
    0.43
    POSITIVE LOGITS
    ru
    0.48
    rups
    0.46
    Rut
    0.44
    ünstler
    0.42
     stop
    0.42
    RUB
    0.42
    érieure
    0.41
    rut
    0.40
    ্যারি
    0.39
     rivulet
    0.39
    Activations Density 0.000%

    No Known Activations