© 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. 132519
    Prev
    Next
    INDEX
    Explanations

    used illicit drugs

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

    economies, investment, users, stakeholders

    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
    ים
    0.66
    ы
    0.55
    ی
    0.54
     לב
    0.54
     zákon
    0.54
    ের
    0.53
    Ὑ
    0.52
     제작
    0.51
    Ordine
    0.50
     במהלך
    0.50
    POSITIVE LOGITS
     n
    0.63
     t
    0.55
    t
    0.53
    this
    0.51
     nt
    0.51
    n
    0.50
     resultant
    0.48
     from
    0.48
    the
    0.48
    ASCII
    0.47
    Activations Density 0.001%

    No Known Activations