© 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. 74856
    Prev
    Next
    INDEX
    Explanations

    noun followed by preposition

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

    breakdown of what happens

    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
    𝙖
    0.47
    𝘢
    0.41
    𝓪
    0.38
     ओर
    0.38
    愀
    0.37
    𝖺
    0.36
    andte
    0.36
     Kana
    0.36
    筝
    0.35
     Entscheidung
    0.35
    POSITIVE LOGITS
     from
    0.57
     från
    0.54
     during
    0.52
     of
    0.51
     trên
    0.49
     on
    0.48
     από
    0.47
     between
    0.42
     من
    0.41
     tijekom
    0.41
    Activations Density 0.107%

    No Known Activations