© 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. 226100
    Prev
    Next
    INDEX
    Explanations

    building a studio together

    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
    身體
    0.47
    ampuan
    0.47
    UNIVERSITY
    0.47
    ⿹
    0.46
    觜
    0.46
     ಪುಟ
    0.45
    wayat
    0.44
    身体
    0.44
     चट
    0.44
    adore
    0.44
    POSITIVE LOGITS
    1
    0.50
     engineer
    0.47
     세율
    0.46
    ફે
    0.45
     Billion
    0.45
     międzynarod
    0.44
     zmniejs
    0.44
     exclude
    0.44
    فين
    0.43
     moderate
    0.43
    Activations Density 0.001%

    No Known Activations