© 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. 5340
    Prev
    Next
    INDEX
    Explanations

    intensifiers followed by descriptive adjectives

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

    intensifiers followed by descriptors

    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
     중에
    0.24
     þat
    0.21
    에서
    0.21
     کہا
    0.20
     vasena
    0.20
     冖
    0.20
     에서
    0.20
     를
    0.20
     फ्रॉम
    0.19
     तपाई
    0.19
    POSITIVE LOGITS
     grueling
    0.24
     ambitious
    0.24
     lucrative
    0.23
     brutal
    0.22
     timid
    0.21
     bizarre
    0.21
     ingenious
    0.21
     tenuous
    0.21
     dismal
    0.21
     hopeful
    0.21
    Activations Density 0.626%

    No Known Activations