© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108793
    Prev
    Next
    INDEX
    Explanations

    names starting with Rosen

    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
    putation
    -0.78
     chansons
    -0.77
     править
    -0.76
     ಮಾ
    -0.73
    asiest
    -0.73
     eyed
    -0.71
     representation
    -0.71
    signee
    -0.71
     Schwä
    -0.70
    carp
    -0.70
    POSITIVE LOGITS
    可见
    0.88
    Seth
    0.83
    Rosen
    0.79
    rivit
    0.76
     Ritual
    0.75
     Rosen
    0.74
    exécution
    0.73
     Seth
    0.72
     CSA
    0.71
     eld
    0.70
    Activations Density 0.028%

    No Known Activations