© 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. 47824
    Prev
    Next
    INDEX
    Explanations

    manifold, group, operator, extension

    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
    ⽉
    -0.93
    信心
    -0.84
     apartament
    -0.83
    تماد
    -0.82
    AFTA
    -0.79
     bono
    -0.77
    attaa
    -0.77
     userData
    -0.77
    cera
    -0.76
     coaxial
    -0.76
    POSITIVE LOGITS
     admit
    4.09
     admits
    4.03
     admitting
    3.63
     Admit
    3.16
     admitted
    3.00
     admite
    2.92
     допуска
    2.72
     admission
    2.67
     admitir
    2.53
    Admission
    2.33
    Activations Density 0.103%

    No Known Activations