© 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. 28047
    Prev
    Next
    INDEX
    Explanations

    introduces explanation

    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
    0
    -2.13
    咐
    -1.98
    罰
    -1.96
    _
    -1.91
    毉
    -1.88
    衝撃
    -1.86
     soggy
    -1.84
     этом
    -1.81
    </sup>
    -1.80
     його
    -1.77
    POSITIVE LOGITS
    I
    2.30
    providedIn
    2.19
     they
    2.14
    *}[
    2.14
    秶
    2.09
     we
    2.06
    
    2.06
    %;
    1.99
    琑
    1.98
    都是
    1.96
    Activations Density 0.031%

    No Known Activations