© 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. 74427
    Prev
    Next
    INDEX
    Explanations

    determinar representation modify

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

    low iron and trees

    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
     করছিলাম
    0.48
    őd
    0.44
     இருந்த
    0.42
     CreateWindow
    0.42
    琐
    0.42
     ورځ
    0.42
     छात्रावास
    0.41
    搭载
    0.41
    褙
    0.41
     ResourceManager
    0.41
    POSITIVE LOGITS
     determinar
    0.50
     tracers
    0.48
     sanct
    0.47
     transpar
    0.47
     entendre
    0.44
     determina
    0.44
     interference
    0.43
     heresy
    0.43
     explicado
    0.43
     believed
    0.42
    Activations Density 0.005%

    No Known Activations