© 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. 63464
    Prev
    Next
    INDEX
    Explanations

    street address

    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
     daarvoor
    -0.82
     acabados
    -0.78
    仟
    -0.76
     Rajan
    -0.74
     Mace
    -0.73
    anych
    -0.70
    矣
    -0.70
    løs
    -0.69
     již
    -0.69
    로운
    -0.69
    POSITIVE LOGITS
     line
    2.83
     lines
    2.39
    line
    2.17
     Line
    2.11
    Line
    2.09
    Lines
    2.03
     línea
    1.98
     Lines
    1.97
    lines
    1.86
     LINE
    1.84
    Activations Density 0.025%

    No Known Activations