© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18973
    Prev
    Next
    INDEX
    Explanations

    Apple and Steve Jobs innovators

    np_acts-logits-general · gemini-2.5-flash-lite

    Silicon Valley tech companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     நோய
    0.50
     दूध
    0.48
     Pharmac
    0.47
     Fishing
    0.47
     FGD
    0.46
     calcareous
    0.46
    ﹟
    0.46
    டுக்க
    0.46
     calving
    0.46
     Aquaculture
    0.45
    POSITIVE LOGITS
     Silicon
    0.95
    Silicon
    0.92
     Cupertino
    0.87
     silicon
    0.77
     Motorola
    0.75
     Huawei
    0.75
     Qualcomm
    0.74
    硅
    0.74
     semiconductor
    0.70
     فناوری
    0.70
    Activations Density 0.207%

    No Known Activations