© 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. 34-GEMMASCOPE-RES-131K
    7. 57873
    Prev
    Next
    INDEX
    Explanations

    told us

    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
     mitochondria
    -0.89
     Jiang
    -0.82
    €
    -0.82
     warunk
    -0.80
    -|
    -0.79
    昵
    -0.79
    =@"
    -0.79
     Kha
    -0.78
     Cha
    -0.77
    pS
    -0.77
    POSITIVE LOGITS
     AllMusic
    1.38
     liner
    1.26
    music
    1.12
     Discogs
    1.11
    Billboard
    1.10
     music
    1.05
    Література
    1.04
     Ahmet
    1.03
    Mojo
    1.03
    izielle
    1.03
    Activations Density 0.114%

    No Known Activations