© 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. 70106
    Prev
    Next
    INDEX
    Explanations

    Texas Hill Country

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

    requests for content generation

    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
    ष्‍
    0.36
    ↵
    0.36
    प्‍
    0.36
    ळे
    0.36
     Hà
    0.35
    volving
    0.35
     Guang
    0.34
     Taehyung
    0.33
     chopsticks
    0.33
    ään
    0.32
    POSITIVE LOGITS
    9
    0.38
    7
    0.36
    8
    0.35
    ד
    0.35
    諡
    0.35
    एर
    0.34
     व्हाउचर
    0.34
     സമര
    0.34
     സുമിത്ര
    0.33
    К
    0.33
    Activations Density 0.396%

    No Known Activations