Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85
    Prev
    Next
    INDEX
    Explanations

    musical chords and lyrics

    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_10/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
     business
    -1.45
     recently
    -1.41
     currently
    -1.32
     new
    -1.27
     now
    -1.23
     dejamos
    -1.23
     soñ
    -1.22
     trabaj
    -1.21
     many
    -1.20
     olho
    -1.20
    POSITIVE LOGITS
    ynchronously
    1.80
    aties
    1.59
     same
    1.48
     zunächst
    1.43
     qed
    1.42
    ¹)
    1.34
    itisation
    1.33
     همان
    1.30
    umers
    1.29
    titial
    1.28
    Activations Density 0.026%

    No Known Activations