© 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. 65193
    Prev
    Next
    INDEX
    Explanations

    words with alle or allen prefixes

    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
     कित
    -0.78
     staggered
    -0.75
    蔺
    -0.75
     glauben
    -0.75
    駅前
    -0.74
     larva
    -0.72
     daylight
    -0.71
    idor
    -0.71
    volvement
    -0.71
     delights
    -0.71
    POSITIVE LOGITS
    Alle
    0.90
     Alle
    0.86
     ALLE
    0.81
     Snackbar
    0.77
    ALLE
    0.77
    kopf
    0.75
    苦
    0.74
    graben
    0.73
    Rtl
    0.73
    eed
    0.72
    Activations Density 0.025%

    No Known Activations