© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103904
    Prev
    Next
    INDEX
    Explanations

    competitors or collaborators

    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
     you
    -1.48
     why
    -1.46
     jego
    -1.35
    lamos
    -1.23
    why
    -1.23
     simply
    -1.22
    なんで
    -1.21
    },
    -1.20
    fficking
    -1.17
    ij
    -1.16
    POSITIVE LOGITS
     from
    1.69
     obrazu
    1.24
     zatem
    1.20
    negara
    1.18
     ͡°
    1.16
     each
    1.15
     richting
    1.13
    tentu
    1.13
     arrêt
    1.12
     РЕ
    1.12
    Activations Density 0.068%

    No Known Activations