© 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. 22-GEMMASCOPE-RES-131K
    7. 68169
    Prev
    Next
    INDEX
    Explanations

    standard system access

    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_22/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
    -1.44
     into
    -1.41
     a
    -1.39
     their
    -1.32
     either
    -1.16
     an
    -1.16
     all
    -1.16
     both
    -1.15
     of
    -1.13
     not
    -1.13
    POSITIVE LOGITS
     gonzález
    1.10
    Beberapa
    1.10
    Contoh
    1.06
    脚注
    1.06
     CALIF
    1.05
     cire
    1.04
     lópez
    1.02
    ώ
    1.02
     tyto
    1.01
    鰊
    1.01
    Activations Density 0.005%

    No Known Activations