© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20640
    Prev
    Next
    INDEX
    Explanations

    AP followed by hyphen

    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
     Several
    -1.41
     Recently
    -1.40
     reconocida
    -1.34
     Behaup
    -1.34
     recientemente
    -1.30
     based
    -1.27
     sejumlah
    -1.27
     Additional
    -1.27
     Sometimes
    -1.26
     neuen
    -1.24
    POSITIVE LOGITS
    ㄱ
    1.60
     bringe
    1.51
     olie
    1.46
     giu
    1.45
     gela
    1.43
     ù
    1.42
    踯
    1.41
     kwe
    1.39
     regionale
    1.37
     fhall
    1.36
    Activations Density 0.009%

    No Known Activations