© 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. 31600
    Prev
    Next
    INDEX
    Explanations

    homogeneous coordinates

    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
    Aç
    -0.81
     выпла
    -0.76
    celular
    -0.74
    authorised
    -0.74
    Amical
    -0.73
    immobili
    -0.71
     consciência
    -0.70
    incredible
    -0.69
    irregular
    -0.69
    nuevos
    -0.69
    POSITIVE LOGITS
     homogeneous
    2.06
     homogenous
    1.84
     homogen
    1.69
    homogeneous
    1.62
     Hom
    1.56
     homog
    1.53
    Hom
    1.51
    hom
    1.51
     homogeneity
    1.34
     homo
    1.23
    Activations Density 0.029%

    No Known Activations