© 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. 46233
    Prev
    Next
    INDEX
    Explanations

    Irish wives

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

    specific technical or foreign words

    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
    Counters
    0.51
    Six
    0.50
    ि
    0.47
    ಾಯಿ
    0.46
    Prices
    0.44
     Six
    0.43
     bred
    0.41
     ವಿ
    0.41
    VIA
    0.41
    ა
    0.41
    POSITIVE LOGITS
    chloric
    0.47
     ciep
    0.46
     EtOAc
    0.45
     உடனடியாக
    0.44
    cante
    0.43
    انات
    0.43
     mutat
    0.42
     अनुर
    0.42
    ندية
    0.42
    ಖ್ಯ
    0.41
    Activations Density 0.000%

    No Known Activations