© 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. 61464
    Prev
    Next
    INDEX
    Explanations

    adverbs describing actions or expressions

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

    speaking softly or quietly

    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
     тщательно
    0.53
    顎
    0.51
    
    0.48
     Ultrasonic
    0.45
     తీవ్ర
    0.44
    털
    0.44
     Ultrasound
    0.43
     глаза
    0.43
     ziemlich
    0.43
     பளி
    0.43
    POSITIVE LOGITS
    ：
    0.58
    :"
    0.51
    ，
    0.49
    ：「
    0.46
    EN
    0.44
     ，
    0.44
    ，《
    0.44
    ICAS
    0.44
    ="
    0.44
    JOIN
    0.44
    Activations Density 0.002%

    No Known Activations