© 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. 85539
    Prev
    Next
    INDEX
    Explanations

    viewDidLoad structure

    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
     også
    -1.58
     then
    -1.58
     Präsentation
    -1.55
     pierws
    -1.45
    inemann
    -1.39
     också
    -1.34
    にあった
    -1.33
     использова
    -1.32
     zunächst
    -1.31
    ция
    -1.30
    POSITIVE LOGITS
    8
    1.52
    ,
    1.47
    -
    1.45
    3
    1.31
    0
    1.30
    𓋼
    1.30
    /
    1.29
    1
    1.29
    ing
    1.28
    they
    1.28
    Activations Density 0.001%

    No Known Activations