© 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. 92878
    Prev
    Next
    INDEX
    Explanations

    durations in weeks

    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
     EARL
    -0.75
     Knoblauch
    -0.75
    racuda
    -0.73
     Nineteenth
    -0.70
    aching
    -0.69
    بیل
    -0.69
    isbury
    -0.69
     minore
    -0.67
    }=\{
    -0.66
     moy
    -0.66
    POSITIVE LOGITS
     eight
    2.81
     six
    2.58
     weeks
    2.36
    eight
    1.97
     four
    1.83
     Eight
    1.74
     seven
    1.70
    Eight
    1.69
     twelve
    1.66
    six
    1.62
    Activations Density 0.096%

    No Known Activations