© 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. 22-GEMMASCOPE-RES-131K
    4. 36227
    Prev
    Next
    INDEX
    Explanations

    this / that / these

    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_22/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
     particularly
    -1.34
     especially
    -1.20
     on
    -1.20
     work
    -1.19
     new
    -1.17
     winter
    -1.13
     suggests
    -1.11
    Four
    -1.10
    ?!”
    -1.09
    <eos>
    -1.09
    POSITIVE LOGITS
     this
    2.33
     این
    1.72
    がこの
    1.49
     هذه
    1.46
    はこの
    1.45
     هذا
    1.41
    この
    1.41
     этого
    1.38
     that
    1.37
    这个
    1.34
    Activations Density 0.043%

    No Known Activations