© 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. 17221
    Prev
    Next
    INDEX
    Explanations

    especially

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

    e.g. examples

    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
    |
    0.39
     /ˈ
    0.38
     kwenye
    0.37
     whose
    0.37
     which
    0.36
                        
    0.36
     IN
    0.36
     n
    0.36
     Â
    0.36
     |
    0.35
    POSITIVE LOGITS
     sobretudo
    0.51
     खासकर
    0.50
    특히
    0.49
     soprattutto
    0.48
     zejména
    0.46
    especially
    0.44
    Especially
    0.41
    特に
    0.40
     особенно
    0.40
     notamment
    0.39
    Activations Density 0.056%

    No Known Activations