© 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. 116226
    Prev
    Next
    INDEX
    Explanations

    persons' names and titles

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

    God, infidelity, timeline, argument

    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
     mentally
    0.51
    나
    0.49
    ي
    0.46
    Щ
    0.46
    ms
    0.44
    neros
    0.44
     enthusi
    0.43
    iah
    0.43
     Homemade
    0.43
     Sensory
    0.43
    POSITIVE LOGITS
    控股
    0.46
     এখনই
    0.46
    涜
    0.45
    比赛
    0.45
    夋
    0.45
    取决于
    0.44
    買う
    0.44
    上市公司
    0.42
    尣
    0.41
    買い
    0.41
    Activations Density 0.005%

    No Known Activations