© 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. 30583
    Prev
    Next
    INDEX
    Explanations

    scientific and fantasy book titles

    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
     cuck
    -0.82
     angka
    -0.81
    回想
    -0.78
    Далее
    -0.76
    ⊖
    -0.75
     Yoda
    -0.75
     DVD
    -0.74
    ใหญ
    -0.73
     minne
    -0.73
    zki
    -0.73
    POSITIVE LOGITS
    ѝ
    0.95
     queer
    0.94
    veyard
    0.93
    ง
    0.92
     Harrow
    0.91
    Ϫ
    0.91
    scryfall
    0.90
    selben
    0.89
    fae
    0.89
    王
    0.89
    Activations Density 0.045%

    No Known Activations