© 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. 116630
    Prev
    Next
    INDEX
    Explanations

    version 2 license

    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
     reempla
    -0.75
    חק
    -0.72
     InkWell
    -0.69
     cacher
    -0.69
    bodies
    -0.68
    UGG
    -0.67
    AHH
    -0.66
     servici
    -0.64
     guider
    -0.63
    vriende
    -0.63
    POSITIVE LOGITS
    คม
    0.68
    ẳng
    0.67
     Argentina
    0.67
     hipó
    0.66
    matmul
    0.66
     K
    0.66
    ってきた
    0.65
    WK
    0.64
     Commission
    0.64
    やはり
    0.64
    Activations Density 0.057%

    No Known Activations