© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156467
    Prev
    Next
    INDEX
    Explanations

    positive sentiment adjectives followed by adverbs

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

    fluctuating, finish, child, profiling

    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_262k_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
     backs
    0.50
     inodes
    0.46
    y
    0.46
    backs
    0.45
    чная
    0.44
     ninh
    0.44
     υ
    0.44
     proporcional
    0.44
     pemasaran
    0.44
     voluntad
    0.43
    POSITIVE LOGITS
    ر
    0.54
     குறிப்பிடத்தக்க
    0.49
     ശ്രീ
    0.47
    地铁
    0.46
    濛
    0.46
    ↵
    0.46
     നേതൃ
    0.45
     från
    0.45
    áni
    0.43
     gesehen
    0.43
    Activations Density 0.000%

    No Known Activations