© 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. 125010
    Prev
    Next
    INDEX
    Explanations

    corporate and financial terms

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

    corporate returns

    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
    thal
    0.55
     ausgestattet
    0.49
     далее
    0.48
     discharged
    0.47
    ৬
    0.47
     আজ
    0.45
    ６
    0.44
     honourable
    0.42
     جواب
    0.42
     गरीब
    0.42
    POSITIVE LOGITS
    Corp
    0.50
    CORPOR
    0.49
    F
    0.48
     CORP
    0.48
    Corpor
    0.46
    DES
    0.45
     Corp
    0.44
    jose
    0.44
    ⋅
    0.44
    Ka
    0.44
    Activations Density 0.000%

    No Known Activations