© 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. 12008
    Prev
    Next
    INDEX
    Explanations

    possibly or maybe

    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
     -
    -1.36
    𝑐
    -1.24
    na
    -1.20
     competi
    -1.18
    旁边的
    -1.17
    eler
    -1.15
    avec
    -1.15
     seraient
    -1.14
     ი
    -1.13
    普通的
    -1.11
    POSITIVE LOGITS
     their
    1.37
    carton
    1.27
    encana
    1.27
    bahaya
    1.23
    éos
    1.23
     farbe
    1.22
    mainan
    1.21
     purchase
    1.20
    ombang
    1.20
     esfera
    1.20
    Activations Density 0.114%

    No Known Activations