© 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. 34-GEMMASCOPE-RES-131K
    7. 541
    Prev
    Next
    INDEX
    Explanations

    [noun] [verb]

    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_34/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
     statement
    -1.06
     suggestions
    -0.91
     expectation
    -0.83
     intention
    -0.83
     petición
    -0.82
     statements
    -0.82
     fulfil
    -0.82
    suggestion
    -0.82
    ーパー
    -0.81
    修改
    -0.80
    POSITIVE LOGITS
    맏
    0.93
    нале
    0.86
    技术的
    0.84
     υπάρχει
    0.82
    لاة
    0.82
     Circumstances
    0.81
     الوزراء
    0.80
    absence
    0.80
     으로
    0.79
    ꕀ
    0.79
    Activations Density 0.114%

    No Known Activations