© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15368
    Prev
    Next
    INDEX
    Explanations

    spiritual guidance and progress

    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
     profundas
    -1.34
     suaves
    -1.28
     seguras
    -1.27
     largas
    -1.26
     necesit
    -1.26
     mengha
    -1.24
     admiti
    -1.23
    珣
    -1.20
     antiguas
    -1.20
     самы
    -1.19
    POSITIVE LOGITS
     and
    1.91
    และ
    1.39
     yaka
    1.17
     into
    1.12
    นี้
    1.11
     from
    1.10
    дость
    1.09
    0
    1.08
     with
    1.06
     each
    1.05
    Activations Density 0.042%

    No Known Activations