© 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. 79174
    Prev
    Next
    INDEX
    Explanations

    cleveland and ohio

    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
    ikawa
    -0.77
    Hec
    -0.75
    Topo
    -0.73
     filet
    -0.73
    Conception
    -0.72
    Median
    -0.72
     tokenize
    -0.71
    Moist
    -0.71
    rfc
    -0.70
     Topo
    -0.70
    POSITIVE LOGITS
    Cleveland
    1.34
     Cleveland
    1.19
    Ohio
    0.82
     Shaker
    0.77
    ASSERT
    0.75
    (**
    0.73
    faces
    0.72
    FACES
    0.71
    Johnson
    0.70
     Squire
    0.70
    Activations Density 0.016%

    No Known Activations