© 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. 73688
    Prev
    Next
    INDEX
    Explanations

    William Hogarth

    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
    ției
    -0.85
    рили
    -0.85
     indeed
    -0.80
    édie
    -0.79
    sibilità
    -0.78
    amoan
    -0.78
    ATL
    -0.78
    писа
    -0.78
    Rigidbody
    -0.78
    før
    -0.77
    POSITIVE LOGITS
     float
    0.80
    более
    0.77
     PayPal
    0.76
    Hadi
    0.75
    afp
    0.72
    orul
    0.71
    Beaver
    0.70
     山口
    0.69
     위해
    0.69
     outlaw
    0.69
    Activations Density 0.005%

    No Known Activations