© 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. 39930
    Prev
    Next
    INDEX
    Explanations

    names and logos

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

    becomes / becoming

    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
     स्टैंडर्ड
    0.49
    كمال
    0.46
     Founding
    0.45
    
    0.43
    IDADE
    0.42
     канцеля
    0.41
    Список
    0.41
     કરીએ
    0.41
     lunghezza
    0.41
     founding
    0.41
    POSITIVE LOGITS
     infr
    0.44
     तेरी
    0.44
     berl
    0.43
    beli
    0.43
     bv
    0.43
     braz
    0.42
     firme
    0.42
    ালন
    0.41
    晋
    0.41
     adenovirus
    0.40
    Activations Density 0.000%

    No Known Activations