© 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. 46913
    Prev
    Next
    INDEX
    Explanations

    designed to

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

    requires careful review

    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
    łączy
    0.45
     பயிற்சிய
    0.45
    빕
    0.45
     Lessor
    0.44
     বেঁচে
    0.43
    also
    0.42
     cũng
    0.41
    ێکی
    0.41
     xứ
    0.40
    ℍ
    0.40
    POSITIVE LOGITS
     accustomed
    0.44
     যেগুলো
    0.43
     निर्णय
    0.42
     ziel
    0.42
    ulation
    0.40
     नती
    0.40
     defiance
    0.39
     uncharted
    0.39
     announcement
    0.39
     tranquillity
    0.39
    Activations Density 0.000%

    No Known Activations