© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92944
    Prev
    Next
    INDEX
    Explanations

    thus, thereby, or concluding remark

    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
    начала
    -0.97
    ないけど
    -0.95
    LOAT
    -0.94
    *)((
    -0.92
     daarom
    -0.91
    SelectedItem
    -0.90
    พาะ
    -0.89
     Meskipun
    -0.88
     pretože
    -0.87
    ржа
    -0.86
    POSITIVE LOGITS
     thus
    8.44
    Thus
    6.03
     Thus
    6.03
    thus
    5.75
     таким
    5.13
     thereby
    5.03
     ainsi
    4.91
    Таким
    4.38
     así
    4.38
     astfel
    4.19
    Activations Density 0.174%

    No Known Activations