© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59659
    Prev
    Next
    INDEX
    Explanations

    ACL civil liberties EFF

    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
    isEmail
    -0.76
    rables
    -0.75
    TSCA
    -0.75
    gigabyte
    -0.75
    envs
    -0.73
    Herzliche
    -0.73
    Übernach
    -0.72
    Inde
    -0.72
     SEGU
    -0.72
    gruß
    -0.71
    POSITIVE LOGITS
     ACL
    3.28
    ACL
    2.05
    AC
    1.60
     acl
    1.49
    acl
    1.49
    CLU
    1.23
    ACLE
    1.18
     civil
    1.17
     American
    1.12
     Civil
    1.12
    Activations Density 0.069%

    No Known Activations