© 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. 70039
    Prev
    Next
    INDEX
    Explanations

    private, facility, fabrication, print

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

    Kazakh and other ethnic groups

    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
     SI
    0.49
     '
    0.46
     gong
    0.46
     bloke
    0.45
     impulse
    0.44
     '//
    0.44
    SIN
    0.44
    SAVE
    0.44
    SI
    0.43
    文
    0.42
    POSITIVE LOGITS
     Utilizing
    0.54
    outed
    0.50
     அதை
    0.47
    inafter
    0.47
     جذاب
    0.47
    initely
    0.46
     उद्ध
    0.46
    𝑜
    0.46
     اتحاد
    0.45
    rizioni
    0.45
    Activations Density 0.001%

    No Known Activations