© 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. 65836
    Prev
    Next
    INDEX
    Explanations

    special measures or administration

    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
    Policy
    -0.82
    POLICY
    -0.81
     sneaky
    -0.76
    Zh
    -0.75
    ingen
    -0.74
    すり
    -0.74
     المن
    -0.72
     работников
    -0.72
    sidian
    -0.71
    usata
    -0.71
    POSITIVE LOGITS
     intervention
    1.41
     receivers
    1.29
     Intervention
    1.19
    intervention
    1.16
     intervene
    1.13
     takeover
    1.11
     corrective
    1.11
    Intervention
    1.09
     appointed
    1.08
     receiver
    1.05
    Activations Density 0.026%

    No Known Activations