© 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. 10-GEMMASCOPE-RES-131K
    7. 130496
    Prev
    Next
    INDEX
    Explanations

    the problem itself

    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
    ఽ
    -1.92
     juſ
    -1.91
     faciliter
    -1.83
     และ
    -1.77
    twenty
    -1.76
    趿
    -1.75
    奩
    -1.75
     télécharger
    -1.75
     graciosos
    -1.73
     imprimer
    -1.70
    POSITIVE LOGITS
     with
    2.41
     only
    2.39
     When
    2.36
     will
    2.22
     not
    2.19
     about
    2.11
     first
    2.08
     most
    2.06
     Since
    2.05
     there
    2.03
    Activations Density 0.040%

    No Known Activations