© 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. 75081
    Prev
    Next
    INDEX
    Explanations

    or download or read

    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
    -1.58
     tirs
    -1.26
     the
    -1.19
     nage
    -1.18
     isra
    -1.17
    OOOO
    -1.16
    uuuu
    -1.16
    weep
    -1.15
    ssystem
    -1.15
     are
    -1.13
    POSITIVE LOGITS
     prioridades
    1.34
     stumble
    1.32
     musíte
    1.29
     immensely
    1.24
    inosa
    1.23
    Londres
    1.22
     alternativas
    1.21
    喏
    1.21
     persönlichen
    1.20
     hoffen
    1.20
    Activations Density 0.133%

    No Known Activations