© 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. 66518
    Prev
    Next
    INDEX
    Explanations

    see or picture

    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
    ところに
    -1.24
    congratulations
    -1.16
    Umm
    -1.14
    以外の
    -1.12
     téléph
    -1.11
    Beginner
    -1.09
     équip
    -1.05
    を探す
    -1.02
     bross
    -1.01
    congrat
    -1.00
    POSITIVE LOGITS
     again
    1.81
    อีก
    1.26
     another
    1.25
     also
    1.17
     two
    1.11
     ponownie
    1.09
    これも
    1.09
    MINUTE
    1.05
     here
    1.04
    です
    1.04
    Activations Density 0.017%

    No Known Activations