© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116156
    Prev
    Next
    INDEX
    Explanations

    copyright and author notices

    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
     escrita
    -0.79
    ült
    -0.73
    atoren
    -0.70
    ſe
    -0.69
    atsu
    -0.68
     Léon
    -0.66
    actividad
    -0.66
     ATK
    -0.66
     трудо
    -0.66
     guerra
    -0.66
    POSITIVE LOGITS
    rye
    0.73
     terbaik
    0.71
     comigo
    0.67
     Relay
    0.67
    Chun
    0.67
    ঙ্
    0.66
     dönt
    0.66
     handleMessage
    0.65
    columnIndex
    0.65
     cancellation
    0.64
    Activations Density 0.082%

    No Known Activations