© 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. 228754
    Prev
    Next
    INDEX
    Explanations

    Elizabeth moved

    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
     Kız
    0.46
    bě
    0.45
    个人的
    0.45
     Cytol
    0.44
    ड़
    0.44
    门
    0.44
    的声音
    0.44
    ਫ
    0.44
    vě
    0.44
    燬
    0.44
    POSITIVE LOGITS
    COO
    0.48
     LAC
    0.47
     lois
    0.47
     Ere
    0.46
    Elli
    0.46
     mannequin
    0.44
    ILE
    0.44
     staggering
    0.44
     lurking
    0.44
     cornerstone
    0.43
    Activations Density 0.001%

    No Known Activations