© 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. 96184
    Prev
    Next
    INDEX
    Explanations

    keywords followed by prepositions/pronouns

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

    introducing definitions or explanations

    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
    𝐠
    0.47
    aspis
    0.47
    yl
    0.43
     actuated
    0.42
    指標
    0.42
     সম্পন্ন
    0.42
     accrue
    0.42
    ák
    0.41
    ус
    0.41
     проектов
    0.41
    POSITIVE LOGITS
    وتی
    0.46
    ه
    0.45
    نا
    0.43
     কাউকে
    0.43
    푥
    0.43
     verletzt
    0.43
    Hi
    0.43
    ν
    0.42
    ना
    0.42
     Burger
    0.42
    Activations Density 0.000%

    No Known Activations