© 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. 105500
    Prev
    Next
    INDEX
    Explanations

    case of

    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
    ordnungen
    -1.65
    stehen
    -1.41
    Liga
    -1.38
    鉿
    -1.35
     antiga
    -1.35
     حمایت
    -1.34
     and
    -1.31
    ėms
    -1.30
    tauchen
    -1.30
    ̨
    -1.27
    POSITIVE LOGITS
    Anyone
    2.11
    Another
    1.84
    only
    1.79
    because
    1.76
    さすがに
    1.75
    これからの
    1.73
    Those
    1.67
    Unfortunately
    1.66
     inzwischen
    1.66
    If
    1.63
    Activations Density 0.017%

    No Known Activations