© 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. 78760
    Prev
    Next
    INDEX
    Explanations

    hemisphere / sphere

    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
    ResumeLayout
    -0.73
    daj
    -0.72
    ونة
    -0.71
    chanter
    -0.69
     pasta
    -0.69
    bernador
    -0.68
    zapatillas
    -0.67
    Advert
    -0.67
     Bambi
    -0.67
    ErrorMsg
    -0.65
    POSITIVE LOGITS
     sphere
    3.36
    sphere
    2.83
     Sphere
    2.77
     spheres
    2.75
    Sphere
    2.55
     sfera
    2.14
    spheres
    2.13
     esfera
    1.92
    pheres
    1.76
    phere
    1.75
    Activations Density 0.050%

    No Known Activations