© 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. 251293
    Prev
    Next
    INDEX
    Explanations

    currency or financial terms

    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
     biennium
    0.51
     reformulation
    0.46
     R
    0.45
     role
    0.45
     duty
    0.44
    attacks
    0.44
     univers
    0.42
     streamlining
    0.42
     hatırl
    0.42
     ROLE
    0.42
    POSITIVE LOGITS
    )$,
    0.53
    Пі
    0.52
    महिलाओं
    0.50
    Основные
    0.49
    Фі
    0.48
    Фи
    0.47
    Сто
    0.47
     ইস্যুতে
    0.47
    Мне
    0.46
    Nu
    0.46
    Activations Density 0.000%

    No Known Activations