© 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. 211417
    Prev
    Next
    INDEX
    Explanations

    rejoice, services, berlin, completely, players, camp

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

    instructions, code, and lists

    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
    xC
    0.54
    𝘾
    0.49
     পরেও
    0.48
    xu
    0.47
    xE
    0.47
     ကျ
    0.46
     ವಿಶ
    0.46
    ପ
    0.46
     किलो
    0.45
    xv
    0.44
    POSITIVE LOGITS
    0.56
    ան
    0.52
     Ron
    0.47
     Retriever
    0.46
    نام
    0.45
     Dade
    0.44
    㳳
    0.44
     Derek
    0.44
     Morgan
    0.43
     Pedro
    0.43
    Activations Density 0.001%

    No Known Activations