© 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. 193265
    Prev
    Next
    INDEX
    Explanations

    is followed by a description

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

    is followed by description

    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
    возмо
    0.46
    ❾
    0.43
    ச்சத்து
    0.42
    дри
    0.40
     аргу
    0.40
    ্ু
    0.39
     aplicado
    0.39
    냄
    0.39
     स्टी
    0.38
     последнего
    0.38
    POSITIVE LOGITS
     দুর্দান্ত
    0.45
     really
    0.45
     lovely
    0.44
     bois
    0.44
     beautiful
    0.44
     freaking
    0.43
     h
    0.42
     ma
    0.42
     Pleistocene
    0.41
     Chinese
    0.41
    Activations Density 0.038%

    No Known Activations