© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201821
    Prev
    Next
    INDEX
    Explanations

    feeling negative emotions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
     Critical
    0.38
    落在
    0.38
    KINS
    0.37
    走
    0.37
    Insets
    0.37
     Ease
    0.36
    CUSSION
    0.36
    +)$
    0.36
     authoritarian
    0.35
     doses
    0.35
    POSITIVE LOGITS
    骠
    0.41
     सिंधु
    0.37
    塙
    0.35
     passato
    0.34
     rent
    0.33
     unanimously
    0.33
    ﺛ
    0.33
     drainage
    0.33
    asn
    0.33
     Drew
    0.33
    Activations Density 0.002%

    No Known Activations