© 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. 234278
    Prev
    Next
    INDEX
    Explanations

    before you, miss out, no electricity

    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
     دری
    0.53
     persever
    0.50
     amplitud
    0.50
    =
    0.47
     repatri
    0.47
     aches
    0.46
    $=
    0.46
     unplug
    0.46
    _
    0.45
    orrag
    0.45
    POSITIVE LOGITS
    іл
    0.52
    劍
    0.51
    餐廳
    0.49
     SCIENCE
    0.48
    做了
    0.45
     Departments
    0.45
     osztály
    0.44
    റ്റു
    0.44
     করিলে
    0.43
    ওল
    0.43
    Activations Density 0.003%

    No Known Activations