© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48009
    Prev
    Next
    INDEX
    Explanations

    working on

    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
    RuntimeObject
    -0.84
     mostrar
    -0.82
     serpiente
    -0.79
    ᴳ
    -0.79
    szer
    -0.78
     jälkeen
    -0.77
     Niles
    -0.77
     ハン
    -0.76
     cellules
    -0.75
    itié
    -0.75
    POSITIVE LOGITS
     on
    2.45
     towards
    0.86
     with
    0.84
     to
    0.84
    取り組
    0.82
     üzerinde
    0.81
     menger
    0.80
     projects
    0.77
    計畫
    0.77
    RSC
    0.76
    Activations Density 0.026%

    No Known Activations