© 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. 212336
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    Investment and financial trends

    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
    ;.
    0.44
    ωμα
    0.44
    成为
    0.43
     .
    0.42
    -
    0.41
    *.
    0.41
    比特
    0.40
    也会
    0.40
    κο
    0.39
    ং
    0.39
    POSITIVE LOGITS
     creativo
    0.50
     responsável
    0.49
     güven
    0.48
     választ
    0.48
     വൃ
    0.47
     pracovní
    0.47
     sabia
    0.46
     recientemente
    0.46
     සම්බන්ධ
    0.46
     kapital
    0.46
    Activations Density 0.000%

    No Known Activations