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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29940
    Prev
    Next
    INDEX
    Explanations

    mindfulness, health metrics, pain, body shape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ีย
    0.46
    אה
    0.45
     conocen
    0.44
     Duniya
    0.44
     bunga
    0.44
    ש
    0.44
    어를
    0.43
    atribut
    0.43
     malah
    0.43
    א
    0.43
    POSITIVE LOGITS
     modèle
    0.60
    ypso
    0.52
    (
    0.50
    omet
    0.46
    imed
    0.46
     Black
    0.45
     “
    0.44
    imus
    0.44
    Impl
    0.44
    pre
    0.43
    Activations Density 0.001%

    No Known Activations