© 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. 99536
    Prev
    Next
    INDEX
    Explanations

    rhyme with || these features

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

    humorous/tech explanations and contexts

    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
    ស្រាយ
    0.40
     வாழ்வில்
    0.40
    凵
    0.39
    இந்தப்
    0.38
    Cucumber
    0.38
     થયો
    0.38
    Capture
    0.37
    অ
    0.37
    危険
    0.37
    ഈ
    0.37
    POSITIVE LOGITS
     måtte
    0.51
     zw
    0.48
     LL
    0.44
     it
    0.44
     と
    0.42
     vort
    0.42
     mitte
    0.42
     als
    0.41
     müsste
    0.41
     ¼
    0.41
    Activations Density 0.001%

    No Known Activations