© 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. 44562
    Prev
    Next
    INDEX
    Explanations

    citations needed, popular vehicle, willing to

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

    numbers, DST, SFT, Gemma, person, Realm

    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
     cyclone
    0.50
     systemat
    0.48
     conoscere
    0.47
    滥
    0.46
     princípios
    0.46
    工程师
    0.44
     progetti
    0.44
     cyclotron
    0.44
    DoS
    0.44
     aplicações
    0.44
    POSITIVE LOGITS
    to
    0.63
     other
    0.54
     to
    0.53
     only
    0.52
    only
    0.47
    م
    0.47
     autres
    0.46
    OTHER
    0.46
    prett
    0.45
    ه
    0.44
    Activations Density 0.001%

    No Known Activations