© 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. 241248
    Prev
    Next
    INDEX
    Explanations

    chain payments Observations

    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
     воен
    0.56
     પ
    0.51
     sevgili
    0.49
     Tae
    0.48
     генерал
    0.48
    tted
    0.48
     древ
    0.47
     quell
    0.47
    lich
    0.46
     ඉතා
    0.45
    POSITIVE LOGITS
    োরে
    0.47
    Introducing
    0.47
     cloths
    0.46
    Artists
    0.46
    "^
    0.46
    ন
    0.46
     fabs
    0.45
    Containers
    0.45
    ierrez
    0.44
    ौरा
    0.43
    Activations Density 0.001%

    No Known Activations