© 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. 10-GEMMASCOPE-RES-131K
    7. 84382
    Prev
    Next
    INDEX
    Explanations

    repeated sequences or abbreviations

    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_10/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
     and
    -3.50
     to
    -2.75
    ↵
    -2.56
    却不
    -2.50
     he
    -2.13
     “
    -2.13
     natuurlijk
    -2.06
    姈
    -2.05
    ichtete
    -2.05
     there
    -2.05
    POSITIVE LOGITS
    t
    3.02
     trésor
    2.83
    是
    2.75
    獁
    2.63
     linken
    2.33
    to
    2.30
     särsk
    2.22
    ſelf
    2.22
    不会
    2.20
    c
    2.17
    Activations Density 0.122%

    No Known Activations