© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75589
    Prev
    Next
    INDEX
    Explanations

    agrees, orders, claims, warrants, declares

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     often
    -1.30
     some
    -1.28
     mostly
    -1.23
     frequently
    -1.18
     usually
    -1.17
     probably
    -1.16
     regularly
    -1.16
     sometimes
    -1.15
     something
    -1.15
     which
    -1.15
    POSITIVE LOGITS
     and
    1.63
    และ
    1.28
     voor
    1.16
    Descriere
    1.09
     to
    1.09
    :
    
    1.07
    rrrrrrrr
    1.06
    atürk
    1.04
    Inches
    1.03
    forKey
    1.02
    Activations Density 0.083%

    No Known Activations