© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54060
    Prev
    Next
    INDEX
    Explanations

    version numbers and commit hashes

    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_34/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
     Lyle
    -0.88
    ⅽ
    -0.76
    鹽
    -0.76
    无可
    -0.75
     extérieur
    -0.74
     proximité
    -0.73
    已有
    -0.73
     asymmetric
    -0.73
     Corse
    -0.73
    りゃ
    -0.72
    POSITIVE LOGITS
    Stab
    0.90
    release
    0.89
    endiendo
    0.85
    dirty
    0.85
     حالی
    0.85
     дата
    0.84
     Tafel
    0.83
    𝘗
    0.83
    branding
    0.82
    SNAPSHOT
    0.82
    Activations Density 0.103%

    No Known Activations