© 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. 83617
    Prev
    Next
    INDEX
    Explanations

    much

    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
    例えば
    -1.08
     كذلك
    -1.03
     manualidades
    -0.99
    inales
    -0.98
     vêtement
    -0.98
     kolei
    -0.95
     decoraciones
    -0.94
     móds
    -0.93
     relâche
    -0.91
     botines
    -0.91
    POSITIVE LOGITS
     much
    6.00
    Much
    3.98
    much
    3.98
     Much
    3.83
     MUCH
    2.75
     to
    2.13
     mycket
    2.09
     mucho
    2.09
     mucha
    1.86
     viel
    1.84
    Activations Density 0.050%

    No Known Activations