© 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. 225475
    Prev
    Next
    INDEX
    Explanations

    financial or service contexts

    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
    א
    0.56
    ל
    0.52
    ן
    0.48
    אל
    0.47
     H
    0.47
     HIF
    0.46
     nasal
    0.45
     TRANSP
    0.45
    ח
    0.45
    קב
    0.44
    POSITIVE LOGITS
    ichte
    0.55
     কাছাকাছি
    0.51
    𝟎
    0.50
    iam
    0.50
     الأمير
    0.50
    ğimiz
    0.49
    ၀၀
    0.48
    iamo
    0.48
     Люди
    0.48
     သူ့
    0.48
    Activations Density 0.000%

    No Known Activations