© 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. 22-GEMMASCOPE-RES-131K
    7. 71129
    Prev
    Next
    INDEX
    Explanations

    past completion or known states

    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
    ฬ
    -1.09
     tertawa
    -0.99
    siąż
    -0.96
     Wikidata
    -0.94
    にいる
    -0.92
    neries
    -0.91
     відповід
    -0.90
    Guillermo
    -0.89
    toThrow
    -0.89
     обуча
    -0.87
    POSITIVE LOGITS
    Already
    1.25
     completed
    1.23
     finished
    1.21
     Already
    1.09
     satisfaction
    1.06
     already
    1.05
     recently
    1.01
     past
    0.98
     уже
    0.96
     Finished
    0.96
    Activations Density 0.124%

    No Known Activations