© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35108
    Prev
    Next
    INDEX
    Explanations

    fridge and its use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    리
    0.99
    ación
    0.90
    atives
    0.89
     as
    0.87
    se
    0.81
    います
    0.79
    ales
    0.78
    cendo
    0.78
    ale
    0.78
    ichannel
    0.78
    POSITIVE LOGITS
    ا
    1.09
    to
    1.05
    на
    1.05
    ா
    1.05
     to
    1.03
    то
    1.03
    ’
    1.02
    ко
    1.00
    та
    0.98
    ни
    0.96
    Activations Density 0.003%

    No Known Activations