© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116382
    Prev
    Next
    INDEX
    Explanations

    directional geographical regions

    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
     admittedly
    -0.87
    Unless
    -0.84
     north
    -0.82
    öny
    -0.80
     equally
    -0.78
     exactly
    -0.78
     nothing
    -0.78
     Urheber
    -0.77
     require
    -0.77
    riever
    -0.77
    POSITIVE LOGITS
     corner
    1.69
     quadrant
    1.57
    corner
    1.47
     Corner
    1.16
    ward
    1.16
    Corner
    1.16
     of
    1.09
     CORNER
    1.05
     quarter
    1.04
    ern
    1.02
    Activations Density 0.024%

    No Known Activations