© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11414
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, separators

    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
    siah
    -1.25
    wouldn
    -1.24
     magnética
    -1.24
     kredi
    -1.24
    returned
    -1.23
    seemed
    -1.23
    もしか
    -1.21
     extravag
    -1.21
    couldn
    -1.21
     gena
    -1.20
    POSITIVE LOGITS
     during
    1.52
     with
    1.38
     for
    1.35
     both
    1.32
     within
    1.28
     time
    1.26
     at
    1.25
     through
    1.19
     that
    1.15
     there
    1.15
    Activations Density 0.013%

    No Known Activations