© 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. 43821
    Prev
    Next
    INDEX
    Explanations

    so + intensifiers

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

    so [descriptor]

    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
    ó
    1.09
    此
    0.86
    nél
    0.82
    大脑
    0.80
    and
    0.79
     P
    0.75
    ल
    0.75
    没有
    0.75
    lade
    0.75
     and
    0.74
    POSITIVE LOGITS
    ان
    1.05
    an
    1.04
    ва
    0.92
     an
    0.91
    おく
    0.84
    e
    0.84
     isn
    0.83
     он
    0.82
    ма
    0.79
    名の
    0.77
    Activations Density 0.080%

    No Known Activations