© 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. 73265
    Prev
    Next
    INDEX
    Explanations

    If a

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

    describing results after a state

    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
    牦
    0.51
     oreille
    0.50
    Gmail
    0.49
    咉
    0.48
    砖
    0.48
    桑
    0.46
    偉
    0.45
    很快
    0.45
     Đầu
    0.45
    按钮
    0.45
    POSITIVE LOGITS
     proliferative
    0.49
    :
    0.48
     Kern
    0.47
    ados
    0.46
     foment
    0.46
    ers
    0.45
     isch
    0.44
     Mana
    0.44
     koron
    0.43
     ad
    0.43
    Activations Density 0.000%

    No Known Activations