© 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. 11141
    Prev
    Next
    INDEX
    Explanations

    PM timestamps

    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
     but
    -1.29
    A
    -1.28
    			
    -1.27
    lgari
    -1.21
     MUCH
    -1.20
     between
    -1.20
    existsSync
    -1.20
    V
    -1.18
     又
    -1.17
    and
    -1.16
    POSITIVE LOGITS
     tatouage
    1.60
     enfance
    1.40
     extré
    1.37
    Keterangan
    1.35
     coute
    1.30
    .
    1.28
     téléphone
    1.28
     levier
    1.27
     île
    1.26
    
    1.23
    Activations Density 0.019%

    No Known Activations