© 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. 34-GEMMASCOPE-RES-131K
    7. 92011
    Prev
    Next
    INDEX
    Explanations

    automatic actions

    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_34/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
    allowing
    -1.31
     cavalier
    -1.15
    故意
    -1.15
     samot
    -1.12
     specif
    -1.10
     schilder
    -1.09
     extravag
    -1.06
     birlikte
    -1.06
     expli
    -1.04
     nötig
    -1.03
    POSITIVE LOGITS
     generated
    1.57
     automatically
    1.47
    Some
    1.38
     assume
    1.38
     created
    1.30
     自动
    1.28
     puts
    1.28
     create
    1.22
     generate
    1.20
     keep
    1.18
    Activations Density 0.038%

    No Known Activations