© 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. 82995
    Prev
    Next
    INDEX
    Explanations

    edge of an abyss

    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
    ksiä
    -0.87
     bersifat
    -0.80
    attled
    -0.79
     Flücht
    -0.76
    editMode
    -0.75
    ariya
    -0.75
    dedor
    -0.74
    Aantal
    -0.74
     Eintritt
    -0.73
     Coastal
    -0.71
    POSITIVE LOGITS
     abyss
    3.30
     Abyss
    2.05
     chasm
    1.88
    aby
    1.87
     pit
    1.87
     botto
    1.86
     depths
    1.78
     void
    1.73
    Aby
    1.73
     aby
    1.62
    Activations Density 0.032%

    No Known Activations