© 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. 93257
    Prev
    Next
    INDEX
    Explanations

    code, names, and topics

    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
     dátum
    -1.16
     llavero
    -1.05
     dourada
    -1.01
    geç
    -0.97
     stratég
    -0.96
     probablemente
    -0.94
    ాల
    -0.94
     cumplido
    -0.94
     fantasmas
    -0.93
     motoru
    -0.92
    POSITIVE LOGITS
    k
    0.97
     (
    0.96
    *)
    0.96
    질
    0.94
    ])
    0.94
    е
    0.91
     adhering
    0.88
    ))
    0.88
    プリング
    0.87
    ten
    0.86
    Activations Density 0.000%

    No Known Activations