© 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. 99690
    Prev
    Next
    INDEX
    Explanations

    health care and highest expectations

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

    handles server-side logic

    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
     Daim
    0.50
    ăl
    0.50
     vagina
    0.48
    頸
    0.44
     unele
    0.43
    ಿಗೆ
    0.43
    縁
    0.43
     പിന്നീ
    0.42
     lagoon
    0.42
    บาง
    0.42
    POSITIVE LOGITS
     habilidades
    0.52
    Beer
    0.50
     desarrolla
    0.50
     ayudar
    0.50
    Development
    0.49
    ↡
    0.49
    Occurrence
    0.49
    شن
    0.48
    Anagram
    0.48
    Exercise
    0.47
    Activations Density 0.000%

    No Known Activations