© 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. 237631
    Prev
    Next
    INDEX
    Explanations

    financial terms and descriptions

    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
    
    0.49
    芏
    0.45
    اقه
    0.44
    英文
    0.44
    اقة
    0.44
     వద్ద
    0.44
     Reclamation
    0.43
    쎌
    0.43
     مدينة
    0.43
    కి
    0.42
    POSITIVE LOGITS
    Anim
    0.44
     coseno
    0.44
     funding
    0.44
    Населення
    0.43
     sostegno
    0.43
    за
    0.43
    Funding
    0.42
    тари
    0.42
     variabel
    0.42
     menikah
    0.42
    Activations Density 0.002%

    No Known Activations