© 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. 112393
    Prev
    Next
    INDEX
    Explanations

    on the road

    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
    慙
    -2.02
     annons
    -1.77
     funktioner
    -1.65
     rajut
    -1.62
     egenskaper
    -1.61
    卨
    -1.61
    เพราะ
    -1.53
            
    -1.51
    焢
    -1.50
     indiri
    -1.47
    POSITIVE LOGITS
    !
    1.80
     In
    1.80
     from
    1.67
    idends
    1.53
     inim
    1.47
    ?
    1.46
    ם
    1.45
    ivers
    1.40
     $-$
    1.39
     življen
    1.38
    Activations Density 0.013%

    No Known Activations