© 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. 80568
    Prev
    Next
    INDEX
    Explanations

    organizations and finance

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

    characters, water, answers, value, understanding, groups, creation

    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
     paradoxical
    0.49
     paradox
    0.47
     ترین
    0.46
    lari
    0.46
     азо
    0.44
     treten
    0.44
    Б
    0.44
    ER
    0.43
    谬
    0.42
    Muhammad
    0.42
    POSITIVE LOGITS
     কথাবার
    0.46
     أهل
    0.43
     retailers
    0.42
     parcels
    0.42
     marketer
    0.41
     پیسے
    0.41
    vart
    0.40
    avorites
    0.39
    uesthouse
    0.39
     সংলাপ
    0.39
    Activations Density 0.003%

    No Known Activations