© 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. 102000
    Prev
    Next
    INDEX
    Explanations

    listing commas

    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
     these
    -2.08
    หรือ
    -1.96
     this
    -1.95
     there
    -1.58
     we
    -1.57
    años
    -1.53
    ácidos
    -1.51
    ᆼ
    -1.51
    entukan
    -1.49
     to
    -1.48
    POSITIVE LOGITS
    j
    2.11
    h
    2.02
    l
    1.97
    k
    1.96
    br
    1.89
    v
    1.88
    c
    1.84
    ate
    1.77
    7
    1.73
    ss
    1.72
    Activations Density 0.167%

    No Known Activations