© 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. 158754
    Prev
    Next
    INDEX
    Explanations

    other languages or concepts

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

    URL, * and issues

    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
     лиде
    0.48
     \{
    0.46
     lider
    0.46
     încep
    0.45
     här
    0.45
     meteen
    0.45
     hükü
    0.44
    ಿದ್ದು
    0.44
     रूपए
    0.43
    โจ
    0.43
    POSITIVE LOGITS
     ಇತರ
    0.54
    anto
    0.49
    -_
    0.49
    OTROS
    0.49
    INTER
    0.47
    ಕರಣ
    0.47
     mengak
    0.47
     замы
    0.46
     initWith
    0.46
    other
    0.45
    Activations Density 0.001%

    No Known Activations