© 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. 54541
    Prev
    Next
    INDEX
    Explanations

    you are / you don

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

    playable ads and your application

    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
     Anlagen
    0.55
    \
    0.50
    2
    0.49
    وا
    0.46
    chter
    0.45
     grafik
    0.44
     Varieties
    0.44
     At
    0.44
     investigating
    0.44
     Ul
    0.43
    POSITIVE LOGITS
     ډ
    0.55
    javaHome
    0.55
     brazen
    0.50
    ađ
    0.49
    områ
    0.48
     ನ್ಯಾಯ
    0.47
    xcodep
    0.46
    áp
    0.46
     قيمه
    0.46
    ému
    0.46
    Activations Density 0.000%

    No Known Activations