© 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. 221980
    Prev
    Next
    INDEX
    Explanations

    admissions offices

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

    comments and dreams

    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
     खेती
    0.56
     फ्लिप
    0.54
    र्न
    0.51
     Premises
    0.47
    𝐣
    0.47
     licences
    0.47
    ᆼ
    0.46
     বাড়
    0.46
    eglasses
    0.46
     είχε
    0.46
    POSITIVE LOGITS
    i
    0.66
    :|
    0.57
    in
    0.53
    |,
    0.50
    |
    0.47
     o
    0.46
    в
    0.46
    мага
    0.45
    A
    0.45
    o
    0.45
    Activations Density 0.001%

    No Known Activations