© 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. 65087
    Prev
    Next
    INDEX
    Explanations

    lists of offerings or groups

    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
    ↵↵
    -1.64
     geholfen
    -1.34
    It
    -1.33
     muertes
    -1.27
     It
    -1.27
    几
    -1.24
     deswegen
    -1.24
     There
    -1.23
     輕
    -1.21
     男孩
    -1.20
    POSITIVE LOGITS
     of
    3.09
    鋲
    1.78
     verbe
    1.48
    𖧵
    1.45
     strategis
    1.41
    蹰
    1.41
     brune
    1.40
     tev
    1.40
     rocha
    1.39
     goud
    1.38
    Activations Density 0.084%

    No Known Activations