© 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. 93094
    Prev
    Next
    INDEX
    Explanations

    citations, especially `[@bbX]`

    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
     such
    -0.91
    hoot
    -0.88
     پہ
    -0.86
     στιγ
    -0.84
     getRule
    -0.81
     雕
    -0.81
    вший
    -0.80
     już
    -0.80
    ...-
    -0.80
     empresarial
    -0.79
    POSITIVE LOGITS
     again
    0.94
     another
    0.90
     neighboring
    0.88
     nuevamente
    0.88
    ∭
    0.83
     glistening
    0.82
    árbol
    0.81
     annexation
    0.79
     帯
    0.79
    Mitglied
    0.78
    Activations Density 0.046%

    No Known Activations