© 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. 2247
    Prev
    Next
    INDEX
    Explanations

    Starts of phrases/words

    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
     strictly
    -0.79
     actually
    -0.77
     especially
    -0.76
    ismi
    -0.76
     }_{
    -0.75
    ılı
    -0.74
    bale
    -0.73
    CELONA
    -0.73
     entirely
    -0.71
     constantly
    -0.69
    POSITIVE LOGITS
    apin
    0.84
     באמצעות
    0.84
    épisode
    0.84
    ỡ
    0.83
    κτήθηκε
    0.82
     présent
    0.80
     renown
    0.79
     urma
    0.79
     ilyen
    0.79
     immovable
    0.78
    Activations Density 0.006%

    No Known Activations