© 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. 5626
    Prev
    Next
    INDEX
    Explanations

    ages, Hindi

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

    Final Fantasy GTA Game

    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
    ↵
    0.52
     misspelled
    0.47
     lovingly
    0.46
     excited
    0.45
     min
    0.45
     donor
    0.45
     can
    0.44
    ut
    0.44
     excitedly
    0.44
     bangs
    0.43
    POSITIVE LOGITS
    Ordine
    0.56
    omens
    0.52
    峈
    0.52
     แบ่ง
    0.51
    ्‍य
    0.50
    städter
    0.50
    Brands
    0.50
    vät
    0.50
    吘
    0.50
    Numeral
    0.49
    Activations Density 0.000%

    No Known Activations