© 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. 170132
    Prev
    Next
    INDEX
    Explanations

    predicting phrases starting with certain words

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

    identify GitHub repositories

    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
     學
    0.47
     hosped
    0.46
     curric
    0.45
     Puebla
    0.44
    ach
    0.44
     selects
    0.44
    irlo
    0.43
     الكتب
    0.43
    ظيف
    0.43
     靴
    0.43
    POSITIVE LOGITS
    लेला
    0.50
    ேத்க
    0.48
    რის
    0.46
    
    0.45
     ধারণা
    0.44
    भारत
    0.43
    passive
    0.43
     Faktor
    0.43
     зміни
    0.42
    animated
    0.42
    Activations Density 0.001%

    No Known Activations