© 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. 10-GEMMASCOPE-RES-131K
    4. 41789
    Prev
    Next
    INDEX
    Explanations

    introducing an explanation

    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
    </b>
    -1.58
     is
    -1.55
     of
    -1.52
    iacute
    -1.40
     depicting
    -1.38
     slew
    -1.38
    —
    -1.35
     including
    -1.34
    County
    -1.32
    Ⅰ
    -1.32
    POSITIVE LOGITS
    ironically
    1.59
     історі
    1.49
     ganancia
    1.48
    
    1.41
    kinda
    1.38
    ipzig
    1.36
    瘊
    1.34
     обладает
    1.34
     wasn
    1.33
    roleum
    1.30
    Activations Density 0.007%

    No Known Activations