© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11569
    Prev
    Next
    INDEX
    Explanations

    perceiving discourse surrounding women

    np_acts-logits-general · gemini-2.5-flash-lite

    user perspectives and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     אם
    0.59
    жа
    0.58
     tendremos
    0.57
     trusty
    0.56
    अगर
    0.54
     מ
    0.52
    אם
    0.52
    за
    0.52
    ફ
    0.52
     או
    0.51
    POSITIVE LOGITS
     perceptions
    0.73
     perceives
    0.70
     discursive
    0.69
     percep
    0.68
     perceiving
    0.68
     perceive
    0.67
     informants
    0.65
     perceived
    0.64
     discourses
    0.63
     discourse
    0.61
    Activations Density 0.167%

    No Known Activations