© 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. 106911
    Prev
    Next
    INDEX
    Explanations

    Anne Frank diary

    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
     Deg
    -0.73
     estuviera
    -0.71
     tornare
    -0.71
     Kopi
    -0.70
    assess
    -0.69
    tas
    -0.69
    Ϲ
    -0.68
     Martini
    -0.68
    picuous
    -0.68
    咣
    -0.67
    POSITIVE LOGITS
     Anne
    1.15
     diary
    1.12
     annex
    1.09
     Diary
    1.08
     Frank
    1.02
    Frank
    0.96
    Anne
    0.94
     Annex
    0.93
    Annex
    0.91
    Diary
    0.89
    Activations Density 0.017%

    No Known Activations