© 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. 201678
    Prev
    Next
    INDEX
    Explanations

    angry because

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

    Brazil currency financial news

    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
    I
    0.68
    T
    0.55
    Avi
    0.53
    Tak
    0.52
    Bell
    0.51
    Krist
    0.51
    Ek
    0.50
    Po
    0.50
    C
    0.50
    주
    0.49
    POSITIVE LOGITS
     breezy
    0.55
     oi
    0.50
     जोड़
    0.49
     piracy
    0.49
     rocky
    0.48
     sulla
    0.48
     serviço
    0.48
     flexing
    0.47
     spiced
    0.47
     derivative
    0.46
    Activations Density 0.000%

    No Known Activations