© 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. 38373
    Prev
    Next
    INDEX
    Explanations

    alex and variations

    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
     alimenti
    -0.82
     need
    -0.80
    แล้ว
    -0.79
    ––
    -0.77
     parts
    -0.77
    égorie
    -0.76
    歪
    -0.76
    AAS
    -0.74
     perlu
    -0.73
     solange
    -0.73
    POSITIVE LOGITS
    ANDER
    1.19
    Алек
    1.10
     Алек
    1.10
    andro
    1.06
    nader
    1.05
    ander
    1.05
    BIÉN
    1.05
    ei
    1.05
    sand
    1.04
    andra
    0.98
    Activations Density 0.013%

    No Known Activations