© 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. 113816
    Prev
    Next
    INDEX
    Explanations

    places followed by descriptors

    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
     camiset
    -2.64
    諼
    -2.53
    鹮
    -2.52
    齜
    -2.44
     ſch
    -2.42
    ፳
    -2.41
    آباد
    -2.36
    一开始
    -2.31
    賅
    -2.31
    娴
    -2.30
    POSITIVE LOGITS
    an
    2.91
     ;
    2.77
    o
    2.73
    V
    2.59
     Considerable
    2.59
    C
    2.56
     delle
    2.56
     t
    2.55
     Confused
    2.50
    J
    2.48
    Activations Density 0.003%

    No Known Activations