© 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. 232725
    Prev
    Next
    INDEX
    Explanations

    phrases introducing descriptors

    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
     zatim
    0.53
     Snapdragon
    0.49
     Semaphore
    0.48
     mums
    0.48
     Thunderbolt
    0.47
     😄
    0.46
     может
    0.46
     Readers
    0.46
     ergonomic
    0.46
     ukulele
    0.45
    POSITIVE LOGITS
    ri
    0.50
    ria
    0.47
    ry
    0.47
    胸
    0.47
    視野
    0.46
    forestation
    0.45
    最低
    0.45
    redd
    0.45
    riere
    0.44
    рб
    0.44
    Activations Density 0.000%

    No Known Activations