© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25799
    Prev
    Next
    INDEX
    Explanations

    emotional connection and support

    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
    Negative Logits
     but
    0.48
    but
    0.45
    and
    0.45
    แต่
    0.45
    len
    0.44
    bins
    0.44
     positions
    0.43
    material
    0.42
    aterial
    0.42
    l
    0.42
    POSITIVE LOGITS
     proteínas
    0.52
     proteína
    0.47
     esposo
    0.46
     correo
    0.45
     chemot
    0.44
    🐹
    0.44
     gacche
    0.44
     पोषक
    0.43
     recetas
    0.43
     emocional
    0.43
    Activations Density 0.002%

    No Known Activations