© 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. 71865
    Prev
    Next
    INDEX
    Explanations

    publication dates

    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
     are
    -3.91
     they
    -2.70
    埽
    -2.64
    ౭
    -2.58
    formatics
    -2.58
     detecta
    -2.44
    睃
    -2.42
    熥
    -2.31
    éroport
    -2.28
     hahaha
    -2.28
    POSITIVE LOGITS
     titolata
    3.03
    ಞ
    2.89
    韞
    2.81
    剮
    2.75
    焄
    2.70
    ↵
    2.69
     betreffenden
    2.63
     vorliegenden
    2.63
     erwähnten
    2.61
     Eigentü
    2.56
    Activations Density 0.033%

    No Known Activations