© 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. 106993
    Prev
    Next
    INDEX
    Explanations

    technical terms and references

    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
    审批
    -0.83
     galaxies
    -0.83
    }/{
    -0.79
    marketing
    -0.79
     trial
    -0.78
    interp
    -0.78
     marketing
    -0.78
    getDevice
    -0.75
     }^{\
    -0.74
     protocols
    -0.73
    POSITIVE LOGITS
    usser
    0.84
    MACHINE
    0.83
    πισ
    0.82
     modality
    0.81
     захворювання
    0.77
    밍
    0.77
    atures
    0.77
    ել
    0.77
    Correction
    0.76
    Открыть
    0.75
    Activations Density 0.057%

    No Known Activations