© 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. 224935
    Prev
    Next
    INDEX
    Explanations

    radio communication

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

    following grammatical

    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
     epis
    0.57
     Y
    0.52
    ش
    0.49
    彰
    0.46
    使
    0.46
     ép
    0.45
     idiom
    0.45
     أبر
    0.44
     organization
    0.44
     romance
    0.44
    POSITIVE LOGITS
    ượu
    0.52
    䍧
    0.47
     ছুটি
    0.46
    ്രീ
    0.46
     njemu
    0.46
    icznych
    0.45
     Đầu
    0.45
    ະພັນ
    0.45
    uretics
    0.45
    Pokud
    0.44
    Activations Density 0.001%

    No Known Activations