© 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. 219064
    Prev
    Next
    INDEX
    Explanations

    founding companies and programs

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

    actions and results

    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
    }\
    0.44
     aspett
    0.43
     يسم
    0.42
    各位
    0.42
    ອີ
    0.41
    }$,
    0.41
     indicato
    0.41
     zobraz
    0.41
    交換
    0.41
     ü
    0.40
    POSITIVE LOGITS
     oversaw
    0.82
     Helped
    0.73
     helped
    0.67
     তিনিই
    0.63
     pioneered
    0.61
     सफलतापूर्वक
    0.59
     दिलाई
    0.59
     त्याने
    0.59
     successfully
    0.57
     oversee
    0.57
    Activations Density 0.177%

    No Known Activations