© 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. 103148
    Prev
    Next
    INDEX
    Explanations

    wow

    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
    ignoire
    -1.04
     concorso
    -0.96
     piccola
    -0.93
     ouvrage
    -0.90
     lampada
    -0.89
     warmth
    -0.88
     якщо
    -0.84
    ensdag
    -0.83
    ESTAMP
    -0.82
    Най
    -0.81
    POSITIVE LOGITS
     Wow
    1.63
    wow
    1.60
     wow
    1.53
     factor
    1.52
    Wow
    1.49
    WOW
    1.47
     Factor
    1.41
     WOW
    1.39
    zers
    1.38
    za
    1.19
    Activations Density 0.010%

    No Known Activations