© 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. 84049
    Prev
    Next
    INDEX
    Explanations

    HTML doctype EN

    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
     dependent
    -0.71
     venne
    -0.68
     multiverse
    -0.65
    dlg
    -0.65
    public
    -0.64
     Vulnerable
    -0.64
     pile
    -0.63
    Chapitre
    -0.62
    ziak
    -0.62
    orig
    -0.62
    POSITIVE LOGITS
    Companies
    0.81
    angliski
    0.77
    ANKS
    0.75
    Managing
    0.75
     CONDITIONS
    0.75
    mediation
    0.74
    Couple
    0.74
    SERVICE
    0.72
    eced
    0.72
    getResult
    0.71
    Activations Density 0.068%

    No Known Activations