© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12579
    Prev
    Next
    INDEX
    Explanations

    especially, especially, especially

    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_22/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
     this
    -1.52
     its
    -1.21
     dieses
    -1.15
    它
    -1.10
     его
    -1.09
     seiner
    -1.08
     or
    -1.07
     was
    -1.02
     seinem
    -1.00
     inputStream
    -0.99
    POSITIVE LOGITS
     they
    2.05
     each
    2.03
     including
    1.97
    except
    1.85
    それぞれ
    1.76
     except
    1.74
    Except
    1.67
     themselves
    1.67
    especially
    1.66
    特に
    1.65
    Activations Density 0.060%

    No Known Activations