© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47531
    Prev
    Next
    INDEX
    Explanations

    introducing specific details

    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
     and
    -1.77
    mal
    -1.57
    "
    -1.32
     sueldo
    -1.30
    롬
    -1.30
     человек
    -1.28
     TextStyle
    -1.28
     POEMS
    -1.27
    COR
    -1.26
     exemplu
    -1.26
    POSITIVE LOGITS
     récemment
    1.81
    各样的
    1.72
    asserole
    1.59
    KELEY
    1.48
     mehrere
    1.48
    −/−
    1.43
    Ꮀ
    1.43
    我希望
    1.43
    tômes
    1.41
    は約
    1.40
    Activations Density 0.026%

    No Known Activations