© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31063
    Prev
    Next
    INDEX
    Explanations

    could be, would be

    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
     then
    -0.87
    ALWAYS
    -0.85
     britann
    -0.82
     combina
    -0.81
    experience
    -0.81
     kombin
    -0.79
    offers
    -0.78
    ës
    -0.77
    always
    -0.77
     toujours
    -0.77
    POSITIVE LOGITS
     easily
    1.30
     rival
    1.23
     mistaken
    1.15
     appeal
    1.09
     belongs
    0.98
     fácilmente
    0.97
    rival
    0.97
     equally
    0.93
     inspire
    0.93
     serve
    0.89
    Activations Density 0.032%

    No Known Activations