© 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. 148628
    Prev
    Next
    INDEX
    Explanations

    a few of the

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

    sunrise and sunset

    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
     Samen
    0.48
    في
    0.46
     IS
    0.46
     in
    0.45
     sunt
    0.45
    </i>
    0.44
    }.
    0.43
    illian
    0.43
    바
    0.42
    ermo
    0.42
    POSITIVE LOGITS
     corrid
    0.50
     değil
    0.46
     hầu
    0.46
     sceGu
    0.46
     cười
    0.45
     recibieron
    0.45
    虻
    0.45
     sàng
    0.45
     çalışmaları
    0.45
     nghiêm
    0.44
    Activations Density 0.000%

    No Known Activations