© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99233
    Prev
    Next
    INDEX
    Explanations

    fields, arrays, and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setelah
    -1.63
    因此
    -1.63
    !
    -1.62
     наиболее
    -1.55
     we
    -1.49
     sollte
    -1.48
     возмо
    -1.48
    !"
    -1.48
    之后
    -1.41
     v
    -1.39
    POSITIVE LOGITS
     antaranya
    2.03
    ㌘
    1.76
    antaranya
    1.67
     poë
    1.60
     demokra
    1.60
     flotte
    1.59
     maksi
    1.59
     abstrak
    1.59
     oran
    1.56
    wakili
    1.56
    Activations Density 5.195%

    No Known Activations