© 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. 34-GEMMASCOPE-RES-131K
    4. 55894
    Prev
    Next
    INDEX
    Explanations

    Led Zeppelin

    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
     Prop
    -0.76
     teleno
    -0.69
    sb
    -0.69
     jitter
    -0.68
     smoothing
    -0.67
    ān
    -0.67
     subscriptions
    -0.67
    莢
    -0.66
     Murdock
    -0.66
     #{
    -0.66
    POSITIVE LOGITS
     Zeppelin
    1.02
     Led
    0.99
     Jimmy
    0.88
    Led
    0.84
    seattle
    0.83
     Lemon
    0.80
    Stair
    0.79
     Kashmir
    0.78
     LIVES
    0.77
     LZ
    0.77
    Activations Density 0.023%

    No Known Activations