© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9572
    Prev
    Next
    INDEX
    Explanations

    states of being idle or idols

    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
    S
    -2.58
    谖
    -2.56
     wöch
    -2.56
    T
    -2.41
    </td>
    -2.38
    en
    -2.34
     verschied
    -2.33
    怍
    -2.31
    R
    -2.27
     accompanied
    -2.25
    POSITIVE LOGITS
    ?"
    2.56
    🐾
    2.47
    ✋
    2.42
     belg
    2.38
     protokol
    2.38
    🌷
    2.36
    🙋
    2.33
    🖐
    2.33
    🎃
    2.30
    🫶
    2.28
    Activations Density 0.010%

    No Known Activations