© 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. 30726
    Prev
    Next
    INDEX
    Explanations

    historic building

    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
    Crowd
    -0.81
     missed
    -0.79
     Hauptstadt
    -0.78
     Chowdhury
    -0.77
     continue
    -0.77
     required
    -0.77
    }(-
    -0.77
     nochmal
    -0.77
    ábamos
    -0.77
    クリル
    -0.77
    POSITIVE LOGITS
     former
    2.39
     converted
    2.36
     old
    2.33
     restored
    2.23
     historic
    2.23
    converted
    2.11
    former
    2.11
     antiguos
    2.09
     century
    2.02
     historical
    2.02
    Activations Density 0.049%

    No Known Activations