© 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. 44459
    Prev
    Next
    INDEX
    Explanations

    academic paper sections

    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
    泚
    -1.35
     PÅ
    -1.30
    breviations
    -1.30
     functie
    -1.28
     today
    -1.27
     aussit
    -1.25
     alpes
    -1.25
    ڰ
    -1.24
    ",
    -1.23
     millioner
    -1.23
    POSITIVE LOGITS
     также
    1.63
     поэтому
    1.48
     also
    1.30
     також
    1.27
     también
    1.26
     altrett
    1.21
    如此
    1.20
     récente
    1.19
    实际上
    1.17
     даже
    1.16
    Activations Density 0.016%

    No Known Activations