© 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. 116309
    Prev
    Next
    INDEX
    Explanations

    legal or financial clauses

    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
     Typically
    -1.23
    Typically
    -1.15
     horrific
    -1.10
     Since
    -1.09
     components
    -1.04
     Ironically
    -1.04
     множество
    -1.02
    už
    -1.02
     typically
    -1.02
    ükemmel
    -1.02
    POSITIVE LOGITS
     said
    1.28
     aforesaid
    1.09
     ALP
    0.94
     embraced
    0.94
     ими
    0.91
     ridu
    0.91
     furia
    0.90
    venty
    0.86
     ..........
    0.86
     comunit
    0.85
    Activations Density 0.037%

    No Known Activations