© 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. 34-GEMMASCOPE-RES-131K
    4. 23757
    Prev
    Next
    INDEX
    Explanations

    versions and chemical prefixes

    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
    ppon
    -0.82
     pir
    -0.79
    xhttp
    -0.79
    QApplication
    -0.79
    licia
    -0.79
    REF
    -0.77
    Finally
    -0.77
     Therapie
    -0.74
    ).—
    -0.74
     reco
    -0.73
    POSITIVE LOGITS
    னு
    0.89
    ász
    0.83
    Mfg
    0.81
     Ergonomic
    0.77
    euvre
    0.75
    思議
    0.74
     weiter
    0.73
    Eind
    0.73
    òs
    0.73
    াল
    0.72
    Activations Density 0.046%

    No Known Activations