© 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. 142924
    Prev
    Next
    INDEX
    Explanations

    site, blog, website, helpful, professionals

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

    words starting with a letter

    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
    themealdb
    0.59
    hcim
    0.52
    íd
    0.52
     figlia
    0.50
     também
    0.49
     роботу
    0.49
     versione
    0.48
    譜
    0.47
    酗
    0.47
    ॓
    0.47
    POSITIVE LOGITS
    ☹
    0.45
    워서
    0.42
    5
    0.40
    efficients
    0.39
     erratic
    0.39
     affluent
    0.39
     advantageous
    0.38
    投入
    0.38
    WELL
    0.38
     favorable
    0.38
    Activations Density 0.001%

    No Known Activations