© 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. 137623
    Prev
    Next
    INDEX
    Explanations

    guide religious upbringing

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

    play One, sometimes, money, already outlined, his teenage

    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
     pox
    0.53
    ش
    0.49
    קל
    0.47
    شون
    0.47
     FINANCE
    0.46
    ეთის
    0.45
    ית
    0.44
     CHAIRMAN
    0.44
     organe
    0.44
    婆
    0.44
    POSITIVE LOGITS
    ጒ
    0.49
    ্দ
    0.46
     христи
    0.46
     स्मिथ
    0.44
    traditional
    0.43
    Wonderful
    0.43
    Сма
    0.43
     нажа
    0.43
    និយាយ
    0.43
    奻
    0.42
    Activations Density 0.001%

    No Known Activations