© 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. 185940
    Prev
    Next
    INDEX
    Explanations

    UPI datelines

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

    mixed language content

    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
     intellect
    0.44
    。
    0.44
    تری
    0.43
     jums
    0.41
     assurer
    0.41
     sizlere
    0.40
     tills
    0.40
    CCA
    0.39
     tink
    0.38
    ਤ
    0.38
    POSITIVE LOGITS
     Cobra
    0.47
    rants
    0.47
     Série
    0.47
    स्पद
    0.47
    辑
    0.47
     phía
    0.47
     Rai
    0.45
     Kiel
    0.45
     Sous
    0.45
    మ్యాచ్
    0.44
    Activations Density 0.000%

    No Known Activations