© 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. 117160
    Prev
    Next
    INDEX
    Explanations

    form fields and sections

    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
     sprá
    -0.85
    buttonText
    -0.75
     REPORTS
    -0.72
     Patricio
    -0.71
    tituts
    -0.71
     estabilidad
    -0.69
    писать
    -0.69
    歌唱
    -0.69
     tárgy
    -0.68
    菀
    -0.68
    POSITIVE LOGITS
     Fields
    1.30
    fieldset
    1.27
    Fields
    1.20
    lapsible
    1.13
     tabs
    1.09
    legend
    1.09
     field
    1.08
    FIELDS
    1.07
     FIELDS
    1.06
     section
    1.05
    Activations Density 0.053%

    No Known Activations