© 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. 22-GEMMASCOPE-RES-131K
    7. 36
    Prev
    Next
    INDEX
    Explanations

    after, final, post

    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_22/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
     onset
    -0.81
     initiation
    -0.81
     οικο
    -0.78
     khởi
    -0.78
    ]--;
    -0.77
     נד
    -0.76
    RequestBuilder
    -0.75
     altern
    -0.75
     Init
    -0.74
    larda
    -0.74
    POSITIVE LOGITS
     після
    1.23
     final
    1.18
     finishing
    1.10
     after
    1.09
     continuation
    1.06
     post
    1.06
    After
    0.98
     finish
    0.97
     pós
    0.96
    Final
    0.94
    Activations Density 0.161%

    No Known Activations