© 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. 34-GEMMASCOPE-RES-131K
    7. 77480
    Prev
    Next
    INDEX
    Explanations

    questions and names like Ruth Langer

    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
    颗粒
    -0.89
     lidi
    -0.76
    зви
    -0.76
     pronon
    -0.73
     apex
    -0.71
    Vous
    -0.71
     tappa
    -0.70
     saldo
    -0.69
    ➩
    -0.69
    Topping
    -0.68
    POSITIVE LOGITS
     food
    0.98
     pherom
    0.96
     punter
    0.88
    food
    0.85
     vux
    0.82
    wag
    0.82
     recruitment
    0.82
    ртуаль
    0.81
     wag
    0.80
     colaborar
    0.79
    Activations Density 0.009%

    No Known Activations