© 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. 59820
    Prev
    Next
    INDEX
    Explanations

    I managed to

    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
    nellement
    -0.84
    bakter
    -0.79
    ﻦ
    -0.75
    tą
    -0.73
    containsKey
    -0.73
    森林
    -0.72
    тата
    -0.72
     станет
    -0.71
    jsonObject
    -0.70
    setLayout
    -0.70
    POSITIVE LOGITS
     managed
    6.31
    managed
    4.91
     manage
    4.63
     Managed
    4.53
    Managed
    4.41
     manages
    3.83
    manage
    3.61
     succeeded
    3.44
     succeed
    3.41
     Manage
    3.33
    Activations Density 0.255%

    No Known Activations