© 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. 197402
    Prev
    Next
    INDEX
    Explanations

    business and finance news

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

    toe, distance, found

    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
     *(
    0.48
     这
    0.47
     今天
    0.46
     **
    0.46
    AN
    0.44
    艾
    0.43
     -"
    0.42
    ahili
    0.41
     "."
    0.41
     拉
    0.40
    POSITIVE LOGITS
    多かった
    0.55
    なか
    0.53
     compleja
    0.51
     मुख्यमंत्री
    0.50
     मध्यप्रदेश
    0.50
    θεν
    0.50
    ésil
    0.49
     kompleks
    0.49
    資金
    0.49
     комплекса
    0.49
    Activations Density 0.001%

    No Known Activations