© 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. 34695
    Prev
    Next
    INDEX
    Explanations

    accept all

    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
    といい
    -0.91
    ynomial
    -0.87
     expects
    -0.87
     legislación
    -0.85
    的角度
    -0.83
     invested
    -0.82
     retained
    -0.81
     especialidad
    -0.81
     ignored
    -0.80
     announcing
    -0.80
    POSITIVE LOGITS
     invitation
    1.76
    invitation
    1.60
     invitations
    1.45
     suggestions
    1.43
     offers
    1.42
     offer
    1.42
     offered
    1.38
     responsibility
    1.32
     challenge
    1.27
     accept
    1.27
    Activations Density 0.023%

    No Known Activations