© 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. 190431
    Prev
    Next
    INDEX
    Explanations

    phrases connecting ideas

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

    melanin, citric, or ethical concepts

    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
     тобто
    0.47
    ાસ
    0.47
    א
    0.46
    ਜ
    0.45
    ᆯ
    0.45
    ก
    0.44
    ЕТ
    0.44
    ਗ
    0.44
    ᅡ
    0.43
    ಿಯ
    0.43
    POSITIVE LOGITS
     melatonin
    0.52
    elu
    0.50
     bac
    0.49
     nylon
    0.48
     mùa
    0.48
     Nylon
    0.48
     photocon
    0.47
     touchdowns
    0.46
     melan
    0.46
     seroton
    0.46
    Activations Density 0.001%

    No Known Activations