© 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. 82554
    Prev
    Next
    INDEX
    Explanations

    existence of things

    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
     comes
    -1.23
     needs
    -1.02
     HAS
    -0.96
     can
    -0.95
     buvo
    -0.94
    ånga
    -0.94
     tendrá
    -0.93
    indak
    -0.93
     becoming
    -0.93
     came
    -0.93
    POSITIVE LOGITS
     is
    1.63
     are
    1.52
     also
    0.97
     inoltre
    0.93
    offsetTop
    0.91
     poème
    0.89
     También
    0.87
     %@",
    0.87
     attente
    0.86
     също
    0.84
    Activations Density 0.047%

    No Known Activations