© 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. 35921
    Prev
    Next
    INDEX
    Explanations

    programming constructs and identifiers

    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
     masculino
    -0.98
    ervices
    -0.94
     mengel
    -0.92
     APPELLANT
    -0.91
    makeText
    -0.88
    ಃ
    -0.87
     Einrichtung
    -0.85
    カップル
    -0.85
    additional
    -0.85
     nächste
    -0.85
    POSITIVE LOGITS
     nephro
    0.96
    </em>
    0.93
     peculiarity
    0.88
     zealand
    0.88
     nephe
    0.86
     jamb
    0.83
     Retrospective
    0.83
     regrettable
    0.82
     adven
    0.82
     timeType
    0.82
    Activations Density 0.005%

    No Known Activations