© 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. 50404
    Prev
    Next
    INDEX
    Explanations

    Bob followed by names

    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
     Proceeding
    -0.80
     senso
    -0.77
    投資
    -0.77
    Ḍ
    -0.74
    لاث
    -0.73
     discernment
    -0.71
     quirks
    -0.71
    íu
    -0.70
    tacles
    -0.69
    韧
    -0.69
    POSITIVE LOGITS
     Bob
    0.99
    Bob
    0.90
     bob
    0.75
     STATES
    0.74
     travail
    0.73
    examined
    0.71
    sistors
    0.70
     charges
    0.70
     poursu
    0.70
     travaille
    0.70
    Activations Density 0.016%

    No Known Activations