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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71151
    Prev
    Next
    INDEX
    Explanations

    death and afterlife journeys

    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
    !!!!!!!
    -1.39
     nějak
    -1.38
    Spolja
    -1.35
    が無い
    -1.35
     înainte
    -1.34
    邉
    -1.33
    饸
    -1.28
    を行い
    -1.27
    ḿ
    -1.27
    镲
    -1.27
    POSITIVE LOGITS
     after
    1.73
     with
    1.49
     on
    1.48
     Probably
    1.38
     will
    1.30
     has
    1.28
     and
    1.24
     by
    1.21
     went
    1.20
     probably
    1.19
    Activations Density 0.001%

    No Known Activations