© 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. 22-GEMMASCOPE-RES-131K
    7. 128545
    Prev
    Next
    INDEX
    Explanations

    error messages

    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_22/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
     both
    -1.69
     despite
    -1.16
     shortly
    -1.16
    日が
    -1.16
     probably
    -1.10
     ironically
    -1.10
     two
    -1.09
     first
    -1.09
     senhora
    -1.09
    与此同时
    -1.09
    POSITIVE LOGITS
     colocando
    1.34
     overly
    1.34
     exceptional
    1.25
     encender
    1.24
     metų
    1.23
     ejemplos
    1.21
    ksy
    1.20
     anerkannt
    1.19
     mirar
    1.18
     الفيلم
    1.18
    Activations Density 0.003%

    No Known Activations