© 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. 175795
    Prev
    Next
    INDEX
    Explanations

    judge today

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

    LTL Shipping

    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
    á
    0.52
    empat
    0.51
    ïd
    0.50
     عبدال
    0.50
     الحكم
    0.50
     فقد
    0.49
    emont
    0.49
    ão
    0.48
     مُ
    0.48
     мо
    0.48
    POSITIVE LOGITS
     Luego
    0.47
    С
    0.47
     Kontext
    0.46
    OLF
    0.46
     crosses
    0.45
     Guys
    0.45
     predicates
    0.45
     Quels
    0.45
     Kreis
    0.44
     Knoten
    0.44
    Activations Density 0.000%

    No Known Activations