© 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. 3680
    Prev
    Next
    INDEX
    Explanations

    numbers followed by . or FM

    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
     What
    -2.81
     Then
    -2.64
     However
    -2.64
     As
    -2.61
     But
    -2.48
    )))),
    -2.31
     Their
    -2.30
     Why
    -2.28
     Both
    -2.27
     replete
    -2.20
    POSITIVE LOGITS
    3
    3.41
    8
    3.36
    6
    3.36
    5
    3.28
    7
    3.13
    2
    3.11
    4
    2.97
    1
    2.84
    鱘
    2.69
    9
    2.64
    Activations Density 0.195%

    No Known Activations