© 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. 81507
    Prev
    Next
    INDEX
    Explanations

    language names

    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
     in
    -1.31
     other
    -1.16
     as
    -1.10
     like
    -1.05
     during
    -0.97
     by
    -0.97
     at
    -0.81
     []:
    -0.78
     based
    -0.78
     (
    -0.78
    POSITIVE LOGITS
     language
    1.24
     языке
    1.15
    ською
    1.12
     языка
    1.11
    াজ
    0.91
    language
    0.90
    디어
    0.86
     körper
    0.86
    riffen
    0.84
     selección
    0.84
    Activations Density 0.007%

    No Known Activations