© 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. 172772
    Prev
    Next
    INDEX
    Explanations

    occupant sensing airbag, electronic stability control

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

    academic tasks and requirements

    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
    Homes
    0.47
    badlogic
    0.45
    Abandoned
    0.44
    Mus
    0.42
    使用的是
    0.42
    缺失
    0.42
    种
    0.42
    ন্যবাদ
    0.41
    ন্ধে
    0.41
    Fisher
    0.41
    POSITIVE LOGITS
     interoper
    0.55
     ਰ
    0.49
     бір
    0.48
     пери
    0.48
    venidas
    0.47
     woven
    0.47
     гостей
    0.47
     १००
    0.46
     ਮ
    0.45
    calar
    0.45
    Activations Density 0.001%

    No Known Activations