© 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. 58730
    Prev
    Next
    INDEX
    Explanations

    actions made by someone or something

    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
    ة
    -1.66
     femen
    -1.54
     ouvre
    -1.50
     gordo
    -1.50
     recomend
    -1.47
     elim
    -1.45
    冏
    -1.44
     ausp
    -1.43
     etern
    -1.42
     neto
    -1.42
    POSITIVE LOGITS
    2
    2.02
    1
    2.02
     These
    2.00
     in
    1.81
    0
    1.74
     Each
    1.56
    4
    1.48
     semasa
    1.41
    8
    1.41
    7
    1.41
    Activations Density 0.113%

    No Known Activations