© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 42137
    Prev
    Next
    INDEX
    Explanations

    e-shopping, packet socket, takes, represents, people, engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enerbah
    0.48
    唿
    0.46
     наказа
    0.45
    នាំ
    0.45
     exhort
    0.44
     जाये
    0.44
     कहे
    0.43
    のですが
    0.43
     सौंप
    0.41
     ابو
    0.41
    POSITIVE LOGITS
     impressive
    0.46
     Linear
    0.45
     Version
    0.45
     (
    0.41
     Residence
    0.41
    The
    0.41
     The
    0.41
     Decoding
    0.41
     E
    0.40
     inc
    0.40
    Activations Density 0.001%

    No Known Activations