© 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. 23543
    Prev
    Next
    INDEX
    Explanations

    indefinite article followed by descriptor

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

    a positive 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
     apportionment
    0.39
     methodology
    0.37
     исследова
    0.37
    Corresponding
    0.37
     পদ্ধতি
    0.36
     গবেষ
    0.36
     sẻ
    0.36
    }{*}{}
    0.36
     apportion
    0.35
     HIV
    0.35
    POSITIVE LOGITS
     sooo
    0.50
     kinda
    0.48
     VERY
    0.48
     soooo
    0.46
    very
    0.44
     very
    0.43
    great
    0.43
     muy
    0.42
    eine
    0.41
     perfeita
    0.41
    Activations Density 0.071%

    No Known Activations