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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18810
    Prev
    Next
    INDEX
    Explanations

    expressing thanks

    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
     indignant
    0.47
     lanç
    0.47
     recast
    0.47
     concur
    0.46
     comienzo
    0.46
     ע
    0.45
     jubil
    0.45
     እነዚህ
    0.45
     admire
    0.45
     bum
    0.44
    POSITIVE LOGITS
     EXPRESS
    0.45
    Compressed
    0.45
    ೇ
    0.43
     Boutique
    0.43
    AY
    0.42
    diameter
    0.42
    was
    0.41
    ONO
    0.41
    人们
    0.40
     proteins
    0.40
    Activations Density 0.018%

    No Known Activations