© 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. 765
    Prev
    Next
    INDEX
    Explanations

    mechanism by which

    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
     lessened
    -1.21
     ‚
    -1.21
     diminished
    -1.20
     maternelle
    -1.17
     diminishes
    -1.16
     diminishing
    -1.16
    recept
    -1.13
     methodology
    -1.09
     immense
    -1.04
     irritated
    -1.04
    POSITIVE LOGITS
     of
    1.59
    mechanism
    1.52
     by
    1.45
     Mechanisms
    1.30
     механи
    1.27
     mecanismo
    1.23
     behind
    1.22
    mechan
    1.20
     Mechanism
    1.18
     mekan
    1.16
    Activations Density 0.051%

    No Known Activations