© 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. 93995
    Prev
    Next
    INDEX
    Explanations

    email signatures precede quotes

    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
     benz
    -0.88
    distas
    -0.87
    ltä
    -0.87
     earnest
    -0.87
    Playback
    -0.86
    enumerable
    -0.85
     Worksheet
    -0.84
    arschu
    -0.84
    чами
    -0.82
    providedIn
    -0.82
    POSITIVE LOGITS
     urmă
    0.85
    סים
    0.85
     >
    0.85
     regarding
    0.83
    >
    0.83
    redmi
    0.81
     greater
    0.78
     groter
    0.76
     bringing
    0.74
    vagrant
    0.73
    Activations Density 0.069%

    No Known Activations