© 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. 25578
    Prev
    Next
    INDEX
    Explanations

    conference

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

    conference name

    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
    豉
    0.48
    マガ
    0.48
    PlayerSelector
    0.47
     streetlight
    0.47
     receptacle
    0.46
     పద
    0.46
     аласыз
    0.46
     lampu
    0.45
    🖕
    0.45
     구독
    0.45
    POSITIVE LOGITS
     conference
    1.12
    conference
    1.09
    Conference
    1.05
     Conference
    1.02
     konfer
    0.97
     सम्मेलन
    0.96
     конферен
    0.95
     Conferences
    0.93
     conferences
    0.88
    conferences
    0.88
    Activations Density 0.154%

    No Known Activations