© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14946
    Prev
    Next
    INDEX
    Explanations

    cost, quantity, relationship

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

    numbers followed by context

    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_16k_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
     Freeman
    0.41
     تعلمنا
    0.41
     Pathway
    0.40
     generalizations
    0.40
    كتب
    0.39
    ‚
    0.39
     sacred
    0.39
     genomics
    0.38
     assunto
    0.38
    ⇨
    0.38
    POSITIVE LOGITS
     বাবার
    0.45
     oğlu
    0.45
     vendeur
    0.44
     나머
    0.44
    間に
    0.44
    दोनों
    0.42
    企業の
    0.41
    entreprise
    0.40
    usahaan
    0.40
     vendedor
    0.40
    Activations Density 0.037%

    No Known Activations