© 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. 8392
    Prev
    Next
    INDEX
    Explanations

    enumerated lists and "etc."

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

    etc. after enumerations

    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
     framebuffer
    0.37
    herence
    0.33
     signalled
    0.33
    ).
    0.32
     appunto
    0.32
    ।
    0.32
     entsprechende
    0.32
    ,
    0.31
    ),
    0.31
     closes
    0.31
    POSITIVE LOGITS
     इत्यादी
    0.49
     etc
    0.46
     എന്നിവ
    0.45
    etc
    0.44
    等は
    0.40
     ইত্যাদি
    0.39
     इत्यादि
    0.39
    などは
    0.38
    等多
    0.38
    などに
    0.38
    Activations Density 0.163%

    No Known Activations