© 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. 63348
    Prev
    Next
    INDEX
    Explanations

    geometric segments or rays

    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
    atological
    -0.86
    Pagination
    -0.84
    kommer
    -0.80
    klasse
    -0.78
    BUR
    -0.77
    IMES
    -0.76
     makro
    -0.75
    钝
    -0.75
     auteurs
    -0.74
     averages
    -0.74
    POSITIVE LOGITS
     AB
    2.36
    AB
    2.06
     AC
    1.59
    BC
    1.46
     BC
    1.44
    AC
    1.24
     OA
    1.20
    ab
    1.19
     ab
    1.16
     AD
    1.15
    Activations Density 0.024%

    No Known Activations