© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39831
    Prev
    Next
    INDEX
    Explanations

    mindfulness, awareness, gratitude, breath

    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
     of
    -1.81
     to
    -1.47
     TÉCN
    -1.20
     gebunden
    -1.20
     It
    -1.19
    uleiro
    -1.18
    他知道
    -1.16
    得很
    -1.13
     ANOTHER
    -1.13
     TÉCNICA
    -1.12
    POSITIVE LOGITS
    tosis
    1.36
    ซ์
    1.30
    Количество
    1.26
    ɴ
    1.26
     yourself
    1.26
     لأنه
    1.25
    ๗
    1.24
    你可以
    1.23
    本日は
    1.23
    ("");
    1.23
    Activations Density 0.027%

    No Known Activations