© 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. 63459
    Prev
    Next
    INDEX
    Explanations

    vital link / Queensland community

    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
    ॆ
    -1.08
     idéia
    -1.04
     STD
    -0.99
     RoHS
    -0.98
    😈
    -0.96
    时光
    -0.95
    ⼿
    -0.94
    ghurt
    -0.93
     aulas
    -0.93
    🕰
    -0.91
    POSITIVE LOGITS
     our
    1.30
     nossos
    1.05
     conversations
    1.05
    . 
    1.03
     COVID
    1.02
    COVID
    1.02
     mahi
    0.98
     nosso
    0.98
     navigate
    0.97
     delirium
    0.95
    Activations Density 0.030%

    No Known Activations