© 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. 10-GEMMASCOPE-RES-131K
    7. 12888
    Prev
    Next
    INDEX
    Explanations

    ages and years

    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
    ↵
    -1.66
     Which
    -1.29
    FID
    -1.26
    u
    -1.25
     облада
    -1.23
    ↵↵↵↵
    -1.20
    certain
    -1.17
     
    -1.13
     сделан
    -1.13
    dz
    -1.13
    POSITIVE LOGITS
     tramo
    1.41
     can
    1.27
     have
    1.26
    According
    1.25
    姣
    1.21
     such
    1.20
    riturismo
    1.19
    0
    1.19
     вместо
    1.17
    未使用
    1.16
    Activations Density 0.037%

    No Known Activations