© 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. 22-GEMMASCOPE-RES-131K
    7. 130080
    Prev
    Next
    INDEX
    Explanations

    asteroid

    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
    他们
    -1.46
     mereka
    -1.21
    之前
    -1.18
    全国
    -1.15
    以前
    -1.13
    SendMessage
    -1.10
    ），
    -1.07
    大
    -1.07
    }).
    -1.06
    ）。
    -1.06
    POSITIVE LOGITS
    ὲν
    1.34
     meditación
    1.26
     fisuras
    1.24
     heridos
    1.20
    一系列
    1.19
     vermutlich
    1.18
    chts
    1.17
    谄
    1.15
     homenagem
    1.14
    醅
    1.14
    Activations Density 0.010%

    No Known Activations