© 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. 78296
    Prev
    Next
    INDEX
    Explanations

    That said

    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
    那是
    -0.94
    それは
    -0.91
    ≫
    -0.90
     mej
    -0.90
     teknis
    -0.88
    锂
    -0.86
     juſt
    -0.86
     secondes
    -0.84
     quello
    -0.84
    THAT
    -0.84
    POSITIVE LOGITS
     said
    6.31
     being
    3.27
    Said
    2.98
    said
    2.77
     Said
    2.69
     gezegd
    2.34
     gesagt
    2.27
    being
    1.94
     étant
    1.93
    Being
    1.90
    Activations Density 0.018%

    No Known Activations